Machine translation - Knowledge (XXG)

1092:

distributions of "Ted" and "Erica" individually, so that the probability of a given name in a specific language will not affect the assigned probability of a translation. A study by Stanford on improving this area of translation gives the examples that different probabilities will be assigned to "David is going for a walk" and "Ankit is going for a walk" for English as a target language due to the different number of occurrences for each name in the training data. A frustrating outcome of the same study by Stanford (and other attempts to improve named recognition translation) is that many times, a decrease in the

1450:(ASL) translations. The program would first analyze the syntactic, grammatical, and morphological aspects of the English text. Following this step, the program accessed a sign synthesizer, which acted as a dictionary for ASL. This synthesizer housed the process one must follow to complete ASL signs, as well as the meanings of these signs. Once the entire text is analyzed and the signs necessary to complete the translation are located in the synthesizer, a computer generated human appeared and would use ASL to sign the English text to the user. 936: 76: 1019:

resolve. For instance, the author of the source text, an Australian physician, cited the example of an epidemic which was declared during World War II in a "Japanese prisoners of war camp". Was he talking about an American camp with Japanese prisoners or a Japanese camp with American prisoners? The English has two senses. It's necessary therefore to do research, maybe to the extent of a phone call to Australia.

916: 48: 1283:. Lawyers who use free translation tools such as Google Translate may accidentally violate client confidentiality by exposing private information to the providers of the translation tools. In addition, there have been arguments that consent for a police search that is obtained with machine translation is invalid, with different courts issuing different verdicts over whether or not these arguments are valid. 697:(the future head of Translation Development AT Google) won DARPA's speed MT competition (2003). More innovations during this time included MOSES, the open-source statistical MT engine (2007), a text/SMS translation service for mobiles in Japan (2008), and a mobile phone with built-in speech-to-speech translation functionality for English, Japanese and Chinese (2009). In 2012, Google announced that 5346: 1401:

sentences are analyzed accuracy is jeopardized. Researchers found that when a program is trained on 203,529 sentence pairings, accuracy actually decreases. The optimal level of training data seems to be just over 100,000 sentences, possibly because as training data increases, the number of possible sentences increases, making it harder to find an exact translation match.

648:(1966), which found that the ten-year-long research had failed to fulfill expectations, funding was greatly reduced. According to a 1972 report by the Director of Defense Research and Engineering (DDR&E), the feasibility of large-scale MT was reestablished by the success of the Logos MT system in translating military manuals into Vietnamese during that conflict. 1428:) being repeatedly pasted into Google Translate, with the resulting translations quickly degrading into nonsensical phrases such as "DECEARING EGG" and "Deep-sea squeeze trees", which are then read in increasingly absurd voices; the full-length version of the video currently has 6.9 million views as of March 2022. 862:, that is a body of text that has been translated into 3 or more languages. Using these methods, a text that has been translated into 2 or more languages may be utilized in combination to provide a more accurate translation into a third language compared with if just one of those source languages were used alone. 1271:

poses a significant challenge to machine translation tools due to its precise nature and atypical use of normal words. For this reason, specialized algorithms have been developed for use in legal contexts. Due to the risk of mistranslations arising from machine translators, researchers recommend that

957:

with the latest advanced MT outputs. Common issues include the translation of ambiguous parts whose correct translation requires common sense-like semantic language processing or context. There can also be errors in the source texts, missing high-quality training data and the severity of frequency of

1255:

Despite being labelled as an unworthy competitor to human translation in 1966 by the Automated Language Processing Advisory Committee put together by the United States government, the quality of machine translation has now been improved to such levels that its application in online collaboration and

1442:

In the early 2000s, options for machine translation between spoken and signed languages were severely limited. It was a common belief that deaf individuals could use traditional translators. However, stress, intonation, pitch, and timing are conveyed much differently in spoken languages compared to

1400:

In addition to disambiguation problems, decreased accuracy can occur due to varying levels of training data for machine translating programs. Both example-based and statistical machine translation rely on a vast array of real example sentences as a base for translation, and when too many or too few

1339:

There are various means for evaluating the output quality of machine translation systems. The oldest is the use of human judges to assess a translation's quality. Even though human evaluation is time-consuming, it is still the most reliable method to compare different systems such as rule-based and

1084:

includes finding the letters in the target language that most closely correspond to the name in the source language. This, however, has been cited as sometimes worsening the quality of translation. For "Southern California" the first word should be translated directly, while the second word should

1036:

One of the major pitfalls of MT is its inability to translate non-standard language with the same accuracy as standard language. Heuristic or statistical based MT takes input from various sources in standard form of a language. Rule-based translation, by nature, does not include common non-standard

643:

Researchers continued to join the field as the Association for Machine Translation and Computational Linguistics was formed in the U.S. (1962) and the National Academy of Sciences formed the Automatic Language Processing Advisory Committee (ALPAC) to study MT (1964). Real progress was much slower,

1371:

of the original text with a reasonable degree of probability. It is certainly true that even purely human-generated translations are prone to error. Therefore, to ensure that a machine-generated translation will be useful to a human being and that publishable-quality translation is achieved, such

1055:, named entities, in a narrow sense, refer to concrete or abstract entities in the real world such as people, organizations, companies, and places that have a proper name: George Washington, Chicago, Microsoft. It also refers to expressions of time, space and quantity such as 1 July 2011, $ 500. 1027:

than has yet been attained. A shallow approach which simply guessed at the sense of the ambiguous English phrase that Piron mentions (based, perhaps, on which kind of prisoner-of-war camp is more often mentioned in a given corpus) would have a reasonable chance of guessing wrong fairly often. A

1104:

While no system provides the ideal of fully automatic high-quality machine translation of unrestricted text, many fully automated systems produce reasonable output. The quality of machine translation is substantially improved if the domain is restricted and controlled. This enables using machine

787:

Interlingual machine translation was one instance of rule-based machine-translation approaches. In this approach, the source language, i.e. the text to be translated, was transformed into an interlingual language, i.e. a "language neutral" representation that is independent of any language. The

675:

called Minitel. Various computer based translation companies were also launched, including Trados (1984), which was the first to develop and market Translation Memory technology (1989), though this is not the same as MT. The first commercial MT system for Russian / English / German-Ukrainian was

2557:

Kocmi, Tom; Avramidis, Eleftherios; Bawden, Rachel; Bojar, Ondřej; Dvorkovich, Anton; Federmann, Christian; Fishel, Mark; Freitag, Markus; Gowda, Thamme; Grundkiewicz, Roman; Haddow, Barry; Koehn, Philipp; Marie, Benjamin; Monz, Christof; Morishita, Makoto (2023). Koehn, Philipp; Haddow, Barry;

1259:

Researchers caution that the use of machine translation in medicine could risk mistranslations that can be dangerous in critical situations. Machine translation can make it easier for doctors to communicate with their patients in day to day activities, but it is recommended to only use machine

1018:

Why does a translator need a whole workday to translate five pages, and not an hour or two? ..... About 90% of an average text corresponds to these simple conditions. But unfortunately, there's the other 10%. It's that part that requires six hours of work. There are ambiguities one has to

1154:

articles and could play a larger role in creating, updating, expanding, and generally improving articles in the future, especially as the MT capabilities may improve. There is a "content translation tool" which allows editors to more easily translate articles across several select languages.

980:. He pointed out that without a "universal encyclopedia", a machine would never be able to distinguish between the two meanings of a word. Today there are numerous approaches designed to overcome this problem. They can be approximately divided into "shallow" approaches and "deep" approaches. 1091:

A third approach is a class-based model. Named entities are replaced with a token to represent their "class"; "Ted" and "Erica" would both be replaced with "person" class token. Then the statistical distribution and use of person names, in general, can be analyzed instead of looking at the

753:

and grammar programs. Its biggest downfall was that everything had to be made explicit: orthographical variation and erroneous input must be made part of the source language analyser in order to cope with it, and lexical selection rules must be written for all instances of ambiguity.

1256:

in the medical field are being investigated. The application of this technology in medical settings where human translators are absent is another topic of research, but difficulties arise due to the importance of accurate translations in medical diagnoses.

884:

has made rapid progress in recent years. However, current consensus is that the so-called human parity achieved is not real, being based wholly on limited domains, language pairs, and certain test benchmarks i.e., it lacks statistical significance power.

983:

Shallow approaches assume no knowledge of the text. They simply apply statistical methods to the words surrounding the ambiguous word. Deep approaches presume a comprehensive knowledge of the word. So far, shallow approaches have been more successful.

1118:

tools enabling mobile business networking between partners speaking different languages, or facilitating both foreign language learning and unaccompanied traveling to foreign countries without the need of the intermediation of a human translator.

2482:

Hendy, Amr; Abdelrehim, Mohamed; Sharaf, Amr; Raunak, Vikas; Gabr, Mohamed; Matsushita, Hitokazu; Kim, Young Jin; Afify, Mohamed; Awadalla, Hany (18 February 2023). "How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation".

792:. The only interlingual machine translation system that was made operational at the commercial level was the KANT system (Nyberg and Mitamura, 1992), which was designed to translate Caterpillar Technical English (CTE) into other languages. 2535:

Thai, Katherine; Karpinska, Marzena; Krishna, Kalpesh; Ray, Bill; Inghilleri, Moira; Wieting, John; Iyyer, Mohit (25 October 2022). "Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature".

1313:

There are many factors that affect how machine translation systems are evaluated. These factors include the intended use of the translation, the nature of the machine translation software, and the nature of the translation process.

1325:(EBMT), but researchers found that when evaluating English to French translation, EBMT performs better. The same concept applies for technical documents, which can be more easily translated by SMT because of their formal language. 682:

MT on the web started with SYSTRAN offering free translation of small texts (1996) and then providing this via AltaVista Babelfish, which racked up 500,000 requests a day (1997). The second free translation service on the web was

2856:"Appendix III of 'The present status of automatic translation of languages', Advances in Computers, vol.1 (1960), p.158-163. Reprinted in Y.Bar-Hillel: Language and information (Reading, Mass.: Addison-Wesley, 1964), p.174-179" 595:) of a rudimentary translation of English into French. Several papers on the topic were published at the time, and even articles in popular journals (for example an article by Cleave and Zacharov in the September 1955 issue of 651:

The French Textile Institute also used MT to translate abstracts from and into French, English, German and Spanish (1970); Brigham Young University started a project to translate Mormon texts by automated translation (1971).

772:

in that it created a translation from an intermediate representation that simulated the meaning of the original sentence. Unlike interlingual MT, it depended partially on the language pair involved in the translation.

1392:

exigencies of the target language require to be resolved. Such research is a necessary prelude to the pre-editing necessary in order to provide input for machine-translation software such that the output will not be

1191:

languages. Within these languages, the focus is on key phrases and quick communication between military members and civilians through the use of mobile phone apps. The Information Processing Technology Office in

1037:

usages. This causes errors in translation from a vernacular source or into colloquial language. Limitations on translation from casual speech present issues in the use of machine translation in mobile devices.

1113:

Machine translation applications have also been released for most mobile devices, including mobile telephones, pocket PCs, PDAs, etc. Due to their portability, such instruments have come to be designated as

1028:

shallow approach that involves "ask the user about each ambiguity" would, by Piron's estimate, only automate about 25% of a professional translator's job, leaving the harder 75% still to be done by a human.

1085:

be transliterated. Machines often transliterate both because they treated them as one entity. Words like these are hard for machine translators, even those with a transliteration component, to process.

1066:

are named entities, and can be further qualified via first name or other information; "president" is not, since Smith could have earlier held another position at Fabrionix, e.g. Vice President. The term

840:. Where such corpora were available, good results were achieved translating similar texts, but such corpora were rare for many language pairs. The first statistical machine translation software was 1295:

in recent years and in low resource machine translation (when only a very limited amount of data and examples are available for training) enabled machine translation for ancient languages, such as

1078:

rating of the translation but would change the text's human readability. They may be omitted from the output translation, which would also have implications for the text's readability and message.

3757: 4867: 848:. In 2005, Google improved its internal translation capabilities by using approximately 200 billion words from United Nations materials to train their system; translation accuracy improved. 994:, wrote that machine translation, at its best, automates the easier part of a translator's job; the harder and more time-consuming part usually involves doing extensive research to resolve 1376:

wrote that machine translation, at its best, automates the easier part of a translator's job; the harder and more time-consuming part usually involves doing extensive research to resolve

2016: 2117:

Machine Translation and the Information Soup: Third Conference of the Association for Machine Translation in the Americas, AMTA'98, Langhorne, PA, USA, October 28–31, 1998 Proceedings

1023:

The ideal deep approach would require the translation software to do all the research necessary for this kind of disambiguation on its own; but this would require a higher degree of

5083: 1515: 4106: 1585: 4266: 2343:

Antonio Toral, Sheila Castilho, Ke Hu, and Andy Way. 2018. Attaining the unattainable? reassessing claims of human parity in neural machine translation. CoRR, abs/1808.10432.

663:, which "pioneered the field under contracts from the U.S. government" in the 1960s, was used by Xerox to translate technical manuals (1978). Beginning in the late 1980s, as 679:

By 1998, "for as little as $ 29.95" one could "buy a program for translating in one direction between English and a major European language of your choice" to run on a PC.

3737: 5377: 3237: 436: 1142:. In 2012, with an aim to replace a rule-based MT by newer, statistical-based MT@EC, The European Commission contributed 3.072 million euros (via its ISA programme). 1088:

Use of a "do-not-translate" list, which has the same end goal – transliteration as opposed to translation. still relies on correct identification of named entities.

3156: 4956: 4860: 3781:. It is impossible however to imagine a literary-translation machine less complex than the human brain itself, with all its knowledge, reading, and discrimination." 2659: 1549: 1510: 583:

in 1949 is perhaps the single most influential publication in the earliest days of machine translation." Others followed. A demonstration was made in 1954 on the

851:

SMT's biggest downfall included it being dependent upon huge amounts of parallel texts, its problems with morphology-rich languages (especially with translating

5392: 4244: 3043: 339: 2969: 2694: 1155:

English-language articles are thought to usually be more comprehensive and less biased than their non-translated equivalents in other languages. As of 2022,

1797: 3896: 3871: 976:

Word-sense disambiguation concerns finding a suitable translation when a word can have more than one meaning. The problem was first raised in the 1950s by

448: 4853: 4079: 4044:. An electronic repository (and bibliography) of articles, books and papers in the field of machine translation and computer-based translation technology 3754: 1534: 1443:

signed languages. Therefore, a deaf individual may misinterpret or become confused about the meaning of written text that is based on a spoken language.

474: 2825: 1074:

Named entities must first be identified in the text; if not, they may be erroneously translated as common nouns, which would most likely not affect the

3688:

Translating and the computer 28. Proceedings of the twenty-eighth international conference on translating and the computer, 16–17 November 2006, London

1958: 4981: 4655: 4099: 2761: 3204:

Automatic Language Processing Advisory Committee, Division of Behavioral Sciences, National Academy of Sciences, National Research Council (1966).

1724: 671:. MT became more popular after the advent of computers. SYSTRAN's first implementation system was implemented in 1988 by the online service of the 5051: 5009: 4824: 1570: 421: 2940: 5387: 5200: 4065: 2029:

wrote about computer-assisted language processing as early as 1957.. was project leader on computational linguistics at Rand from 1955 to 1968.

2006: 3695: 2802: 2591: 1818: 1437: 308: 283: 5170: 4888: 4565: 4256: 4092: 3129: 1333: 801: 4057: 2731: 1446:

Researchers Zhao, et al. (2000), developed a prototype called TEAM (translation from English to ASL by machine) that completed English to

3533: 2275:. Paper presented at the 45th Annual Meeting of the Association for Computational Linguistics, June 23–30, 2007, Prague, Czech Republic. 1470:

protection, so some scholars claim that machine translation results are not entitled to copyright protection because MT does not involve

5289: 5029: 4949: 4819: 1907:, which reported in 1964 as that reached the power level over the score of 90-point on the textbook of first grade of junior hi-school.) 1260:

translation when there is no other alternative, and that translated medical texts should be reviewed by human translators for accuracy.

1697: 5382: 4898: 4426: 2630:. Costa-jussà, Marta R., Rapp, Reinhard, Lambert, Patrik, Eberle, Kurt, Banchs, Rafael E., Babych, Bogdan. Switzerland. 21 July 2016. 1640: 907:

to translate a text. This approach is considered promising, but is still more resource-intensive than specialized translation models.

904: 763: 334: 2432: 2209: 1105:

translation as a tool to speed up and simplify translations, as well as producing flawed but useful low-cost or ad-hoc translations.

892:, which is thought to usually deliver the best machine translation results as of 2022, typically still need post-editing by a human. 426: 4908: 4580: 4411: 3949: 3708: 2992: 2796: 2635: 2189: 2099: 1989: 1763: 1322: 1308: 1216:

on the web in recent years has created yet another niche for the application of machine translation software – in utilities such as

714: 416: 324: 3559: 625:

system in 1954. MT research programs popped up in Japan and Russia (1955), and the first MT conference was held in London (1956).

4913: 4351: 2855: 2276: 1247:

gained popularity in Japan because of its machine translation features allowing players from different countries to communicate.

782: 769: 1857: 958:

several types of problems may not get reduced with techniques used to date, requiring some level of human active participation.

5091: 4903: 4768: 4421: 3802: 3309:"Understanding the societal impacts of machine translation: a critical review of the literature on medical and legal use cases" 1625: 1345: 1318: 1093: 1075: 819: 668: 506: 35: 3734: 3679: 1923: 691:

wrote in 1998 that "Systran's Babelfish and GlobaLink's Comprende" handled "Don't bank on it" with a "competent performance."

5153: 5131: 4942: 4893: 4416: 4161: 2124: 2050: 1888: 1554: 744: 631:"wrote about computer-assisted language processing as early as 1957" and "was project leader on computational linguistics at 588: 560:, which are used in modern machine translation. The idea of machine translation later appeared in the 17th century. In 1629, 526: 502: 467: 390: 196: 3212: 2611: 2457: 3368:"Assessing the Use of Google Translate for Spanish and Chinese Translations of Emergency Department Discharge Instructions" 5350: 5316: 4685: 4406: 3152: 1645: 1580: 1525: 1138:

Despite their inherent limitations, MT programs are used around the world. Probably the largest institutional user is the

237: 222: 31: 2241: 5397: 5372: 4378: 3472:"The Use of Machine Translation for Outreach and Health Communication in Epidemiology and Public Health: Scoping Review" 1544: 1292: 3017: 4723: 4708: 4680: 4545: 4540: 4115: 3070: 1539: 360: 329: 155: 3282: 2833: 2965: 2702:. Paper presented at the 7th International EAMT Workshop on MT and Other Language Technology Tools... Archived from 567:

The idea of using digital computers for translation of natural languages was proposed as early as 1947 by England's

5321: 5257: 4923: 4918: 4460: 4431: 4209: 3766:

Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012): Posters, pages 441–450

3582: 2663: 2149: 1595: 1180: 881: 871: 710: 510: 2913: 2703: 5304: 5264: 4303: 4156: 1832: 1559: 1520: 991: 967: 622: 460: 3888: 100: 5076: 4829: 4753: 4485: 4441: 4326: 4224: 3868: 1272:

machine translations should be reviewed by human translators for accuracy, and some courts prohibit its use in

971: 724: 411: 3794: 2303:"Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages" 1336:

system has produced satisfactory translations that require no human intervention save for quality inspection.

3777:

J.M. Cohen observes (p.14): "Scientific translation is the aim of an age that would reduce all activities to

2240:. Paper presented at the 8th Biennial Conference of the Association for Machine Translation in the Americas. 1895:わが国では1956年、当時の電気試験所が英和翻訳専用機「ヤマト」を実験している。この機械は1962年頃には中学1年の教科書で90点以上の能力に達したと報告されている。(translation (assisted by 5269: 5242: 5071: 5004: 4733: 4703: 4370: 4080:

From Classroom to Real World: How Machine Translation is Changing the Landscape of Foreign Language Learning

1946: 1780: 927: 293: 201: 140: 115: 3581:

Gutherz, Gai; Gordin, Shai; Sáenz, Luis; Levy, Omer; Berant, Jonathan (2 May 2023). Kearns, Michael (ed.).

1900: 1122:

For example, the Google Translate app allows foreigners to quickly translate text in their surrounding via

5279: 5274: 5247: 5165: 4590: 4283: 4261: 4251: 4219: 4194: 4021: 3923: 3641:

Way, Andy; Nano Gough (20 September 2005). "Comparing Example-Based and Statistical Machine Translation".

2891: 2752: 2353:

Yvette, Graham; Barry, Haddow; Koehn, Philipp (2019). "Translationese in Machine Translation Evaluation".

1671: 1620: 1447: 1394: 1368: 1280: 1188: 1052: 576: 376: 262: 160: 130: 39: 4033: 621:

MT research team, led by Professor Michael Zarechnak, followed (1951) with a public demonstration of its

5205: 4965: 4450: 1732: 1564: 1405: 618: 431: 288: 191: 135: 120: 5252: 5215: 5195: 5111: 4992: 4803: 4479: 4455: 4308: 3892: 3424: 3335: 3251:

Randhawa, Gurdeeshpal; Ferreyra, Mariella; Ahmed, Rukhsana; Ezzat, Omar; Pottie, Kevin (April 2013).

3231: 2561:

Findings of the 2023 Conference on Machine Translation (WMT23): LLMs Are Here but Not Quite There Yet

2505: 2387: 1650: 1505: 900: 684: 601:). A similar application, also pioneered at Birkbeck College at the time, was reading and composing 592: 514: 443: 303: 298: 145: 59: 4062: 3179: 1164: 1156: 949:. The broken Chinese sentence sounds like "there does not exist an entry" or "have not entered yet". 5309: 5284: 5121: 5096: 4783: 4713: 4670: 4626: 4388: 4383: 4271: 4013: 2786: 1389: 1329: 1197: 1139: 1007: 977: 837: 825: 614: 568: 370: 186: 176: 150: 125: 2588: 2506:"Study assesses the quality of AI literary translations by comparing them with human translations" 1160: 5326: 5039: 5024: 4997: 4793: 4665: 4530: 4293: 4276: 4134: 3995: 3977: 3815: 3658: 3452: 3348: 3121: 2653: 2537: 2484: 2413: 2354: 2314: 2011: 1824: 1635: 1615: 1590: 1529: 1201: 1127: 1115: 953:

Studies using human evaluation (e.g. by professional literary translators or human readers) have

896: 549: 232: 110: 105: 1204:. US Air Force has awarded a $ 1 million contract to develop a language translation technology. 3425:"Plurilingualism, multimodality and machine translation in medical consultations: A case study" 2728: 1096:

scores for translation will result from the inclusion of methods for named entity translation.

5148: 5101: 4798: 4510: 4318: 4229: 3968:

Weber, Steven; Mehandru, Nikita (2022). "The 2020s Political Economy of Machine Translation".

3945: 3833: 3691: 3620: 3602: 3511: 3493: 3444: 3405: 3387: 3340: 3274: 2792: 2641: 2631: 2405: 2185: 2120: 2095: 2075: 2046: 1985: 1884: 1814: 1759: 1296: 1221: 1213: 1123: 935: 672: 564:

proposed a universal language, with equivalent ideas in different tongues sharing one symbol.

561: 355: 206: 90: 841: 5294: 5210: 5126: 5106: 5061: 5056: 4675: 4560: 4535: 4336: 4239: 4041: 3987: 3933: 3650: 3610: 3594: 3501: 3483: 3436: 3395: 3379: 3330: 3320: 3264: 2569: 2395: 2324: 1896: 1839: 1806: 1575: 1364: 1273: 1068: 889: 789: 698: 632: 381: 1363:

Relying exclusively on unedited machine translation ignores the fact that communication in

4787: 4748: 4743: 4611: 4341: 4214: 4189: 4171: 4069: 4037: 4025: 3875: 3798: 3761: 3741: 3683: 2735: 2615: 2595: 2205: 1475: 1184: 1081: 954: 946: 833: 694: 386: 365: 75: 3712: 1126:

using the smartphone camera that overlays the translated text onto the text. It can also

498:

to another, including the contextual, idiomatic and pragmatic nuances of both languages.

3615: 3506: 3471: 2391: 5299: 5019: 4495: 4475: 4199: 3938: 3400: 3367: 3366:

Khoong, Elaine C.; Steinbrook, Eric; Brown, Cortlyn; Fernandez, Alicia (1 April 2019).

3269: 1279:

The use of machine translation in law has raised concerns about translation errors and

597: 3211:(Report). Washington, D. C.: National Research Council, National Academy of Sciences. 2862: 2267: 895:

Instead of training specialized translation models on parallel datasets, one can also

5366: 5331: 5158: 4758: 4570: 4550: 4331: 3999: 3456: 3352: 2417: 2302: 1853: 1828: 1459: 1349: 1268: 1236:, etc. – allowing users speaking different languages to communicate with each other. 1233: 877: 720: 628: 580: 572: 545: 541: 278: 181: 17: 4845: 3383: 3044:"Content translation tool helps create over half a million Knowledge (XXG) articles" 2589:

Milestones in machine translation – No.6: Bar-Hillel and the nonfeasibility of FAHQT

2269:

Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora

2142:"Babel Fish: What Happened To The Original Translation Application?: We Investigate" 915: 47: 5235: 5066: 5034: 4738: 3676: 3662: 2676: 1919: 1373: 1046: 987: 750: 3325: 3308: 2729:

Name Translation in Statistical Machine Translation Learning When to Transliterate

1151: 3677:

Fully Automatic High Quality Machine Translation of Restricted Text: A Case Study

3205: 2608: 810:

entries, which means that the words were translated as they are by a dictionary.

5230: 5225: 5046: 4695: 4575: 4288: 4204: 4181: 4129: 3755:

LEPOR: A Robust Evaluation Metric for Machine Translation with Augmented Factors

3598: 1630: 1610: 1605: 1500: 1479: 1463: 1385: 1381: 1229: 1011: 1003: 999: 859: 664: 553: 491: 257: 252: 95: 67: 2574: 2400: 2375: 2232: 749:

The rule-based machine translation approach was used mostly in the creation of

5190: 4298: 4084: 4051: 3851: 3778: 3654: 1487: 1471: 1071:

is what defines these usages for analysis in statistical machine translation.

807: 557: 406: 3606: 3497: 3448: 3391: 3344: 2696:

Improving Machine Translation Quality with Automatic Named Entity Recognition

2645: 2607:

Bar-Hillel (1960), "Automatic Translation of Languages". Available online at

1805:. Studies in the History of the Language Sciences. Vol. 97. p. 17. 1167:

each only have over 2.5 million articles, each often far less comprehensive.

5220: 4166: 4075:

Slator News & analysis of the latest developments in machine translation

1810: 1600: 1467: 1424: 1377: 1244: 995: 919:

Machine translation could produce some non-understandable phrases, such as "

732: 247: 3624: 3515: 3409: 3278: 2788:

Melby, Alan. The Possibility of Language (Amsterdam:Benjamins, 1995, 27–41)

2409: 1725:"The Cryptological Origins of Machine Translation: From al-Kindi to Weaver" 4074: 3440: 3307:

Vieira, Lucas Nunes; O’Hagan, Minako; O’Sullivan, Carol (18 August 2021).

3252: 1947:"Speaking in Tongues: Science's centuries-long hunt for a common language" 1698:"Google Translate vs. ChatGPT: Which One Is the Best Language Translator?" 1328:

In certain applications, however, e.g., product descriptions written in a

5141: 5116: 4641: 4621: 4606: 4585: 4555: 4500: 4465: 4346: 1418: 1413: 1341: 1217: 537: 495: 4934: 3991: 3867:

Zhao, L., Kipper, K., Schuler, W., Vogler, C., & Palmer, M. (2000).

3791: 2559: 2141: 4778: 4636: 4616: 4490: 4234: 4149: 2568:. Singapore: Association for Computational Linguistics. pp. 1–42. 1409: 829: 660: 602: 242: 3534:"Man v. Machine: Social and Legal Implications of Machine Translation" 2329: 1982:

Scientific Babel: How Science Was Done Before and After Global English

1317:

Different programs may work well for different purposes. For example,

667:

power increased and became less expensive, more interest was shown in

544:

who developed techniques for systemic language translation, including

4144: 4139: 2941:"Google Translate app update said to make speech-to-text even easier" 1483: 1353: 824:

Statistical machine translation tried to generate translations using

728: 536:

The origins of machine translation can be traced back to the work of

401: 396: 723:

methods, statistical methods required a lot of rules accompanied by

3982: 3869:

A Machine Translation System from English to American Sign Language

2542: 2489: 2359: 1179:, the U.S. and its allies have been most interested in developing 701:

translates roughly enough text to fill 1 million books in one day.

5136: 4834: 4470: 3488: 3180:"Korean Games Growing in Popularity in Tough Japanese Game Market" 2319: 1357: 1225: 1193: 934: 914: 645: 584: 46: 3583:"Translating Akkadian to English with neural machine translation" 3095: 1367:

is context-embedded and that it takes a person to comprehend the

832:

corpus, the English-French record of the Canadian parliament and

4356: 4047: 3018:"Knowledge (XXG) taps Google to help editors translate articles" 1901:

National Institute of Advanced Industrial Science and Technology

1486:

when a work is translated: a translator must have permission to

1176: 855:

such languages), and its inability to correct singleton errors.

4938: 4849: 4088: 4018: 3470:

Herrera-Espejel, Paula Sofia; Rach, Stefan (20 November 2023).

3206:

Language and Machines: Computers in Translation and Linguistics

2887: 2376:"Poor English skills? New AIs help researchers to write better" 4631: 3071:"Knowledge (XXG) Has a Language Problem. Here's How To Fix It" 2007:"David G. Hays, 66, a Developer Of Language Study by Computer" 1903:(AIST) tested the proper English-Japanese translation machine 1372:

translations must be reviewed and edited by a human. The late

845: 4030: 2914:"Google Translate Adds 20 Languages To Augmented Reality App" 2754:

Using Named Entity Recognition to improve Machine Translation

2115:

Farwell, David; Gerber, Laurie; Hovy, Eduard (29 June 2003).

1796:

J. Hutchins (2000). "Warren Weaver and the launching of MT".

1175:

Following terrorist attacks in Western countries, including

858:

Some work has been done in the utilization of multiparallel

2888:"Human quality machine translation solution by Ta with you" 2566:

Proceedings of the Eighth Conference on Machine Translation

2073:

Budiansky, Stephen (December 1998). "Lost in Translation".

1756:

Universal Language Schemes in England and France, 1600-1800

1058:

In the sentence "Smith is the president of Fabrionix" both

1024: 3735:

Machine translation as a tool in second language learning

2433:"DeepL: An Exceptionally Magnificent Language Translator" 1779:

Booth, Andrew D. (1 May 1953). "MECHANICAL TRANSLATION".

4019:

International Association for Machine Translation (IAMT)

3709:"Comparison of MT systems by human evaluation, May 2008" 990:, a long-time translator for the United Nations and the 51:

A mobile phone app translating Spanish text into English

4014:

The Advantages and Disadvantages of Machine Translation

3560:"New Mexico's Success with Non-English Speaking Jurors" 3153:"GCN – Air force wants to build a universal translator" 2738:. Association for Computational Linguistics. 389–397. 2068: 2066: 2064: 2062: 1150:

Machine translation has also been used for translating

3959:

Lewis-Kraus, Gideon (7 June 2015). "Tower of Babble".

2458:"DeepL outperforms Google Translate – DW – 12/05/2018" 1516:

Comparison of different machine translation approaches

1586:

List of research laboratories for machine translation

2683:(The Language Challenge), Paris, L'Harmattan, 1994. 5183: 4979: 4972: 4812: 4767: 4722: 4694: 4654: 4599: 4521: 4509: 4440: 4397: 4369: 4317: 4180: 4122: 3816:"4 times Google Translate totally dropped the ball" 2727:Hermajakob, U., Knight, K., & Hal, D. (2008). 3937: 3889:"Machine Translation: No Copyright On The Result?" 1984:. Chicago, Illinois: University of Chicago Press. 768:Transfer-based machine translation was similar to 27:Computerized translation between natural languages 3878:. Lecture Notes in Computer Science, 1934: 54–67. 3834:"回数を重ねるほど狂っていく Google翻訳で「えぐ」を英訳すると奇妙な世界に迷い込むと話題に" 2826:"A Simple Model Outlining Translation Technology" 2530: 2528: 2526: 1404:Flaws in machine translation have been noted for 4048:Machine translation (computer-based translation) 3863: 3861: 3253:"Using machine translation in clinical practice" 2993:"Knowledge (XXG) has a Google Translate problem" 2182:Routledge Encyclopedia of Translation Technology 1672:"Google Translate Gets a Deep-Learning Upgrade" 1016: 3636: 3634: 2609:http://www.mt-archive.info/Bar-Hillel-1960.pdf 1550:Fuzzy matching (computer-assisted translation) 1511:Comparison of machine translation applications 788:target language was then generated out of the 676:developed at Kharkov State University (1991). 509:. These methods have since been superseded by 4950: 4861: 4100: 1782:Computers and Automation 1953-05: Vol 2 Iss 4 940: 920: 828:based on bilingual text corpora, such as the 579:in the same year. "The memorandum written by 468: 8: 3236:: CS1 maint: multiple names: authors list ( 2045:(in Japanese). Tokyo: (株)ラッセル社. p. 16. 1883:(in Japanese). Tokyo: (株)ラッセル社. p. 16. 2307:Journal of Artificial Intelligence Research 2206:"Google Translator: The Universal Language" 1482:in the original language does not lose his 806:Machine translation used a method based on 5345: 4976: 4957: 4943: 4935: 4868: 4854: 4846: 4518: 4314: 4107: 4093: 4085: 4058:Machine Translation and Minority Languages 4050:– Publications by John Hutchins (includes 2658:: CS1 maint: location missing publisher ( 1535:Controlled language in machine translation 1299:and its dialects Babylonian and Assyrian. 669:statistical models for machine translation 475: 461: 54: 3981: 3614: 3505: 3487: 3399: 3336:1983/29727bd1-a1ae-4600-9e8e-018f11ec75fb 3334: 3324: 3268: 2890:(in Spanish). Tauyou.com. 15 April 2009. 2746: 2744: 2693:Babych, Bogdan; Hartley, Anthony (2003). 2573: 2541: 2488: 2399: 2358: 2328: 2318: 2208:. Blog.outer-court.com. 25 January 2007. 4054:of several books on machine translation) 3792:annually performed NIST tests since 2001 3313:Information, Communication & Society 2628:Hybrid approaches to machine translation 1758:. Toronto: University of Toronto Press. 1432:Machine translation and signed languages 1159:has over 6.5 million articles while the 955:systematically identified various issues 5378:Applications of artificial intelligence 5052:Carbon nanotube field-effect transistor 5010:Applications of artificial intelligence 1854:"Warren Weaver, American mathematician" 1663: 1571:Language and Communication Technologies 347: 316: 270: 214: 168: 82: 66: 5201:Differential technological development 3940:An Introduction to Machine Translation 3302: 3300: 3229: 3122:"Machine Translation for the Military" 2894:from the original on 22 September 2009 2651: 2266:Cohn, Trevor; Lapata, Mirella (2007). 1631:Translation § Machine translation 617:, began his research at MIT (1951). A 490:is use of computational techniques to 427:Bhagavad-gita translations by language 3899:from the original on 29 November 2012 3527: 3525: 3151:Jackson, William (9 September 2003). 2972:from the original on 8 September 2013 2301:Nakov, Preslav; Ng, Hwee Tou (2012). 2212:from the original on 20 November 2008 2152:from the original on 20 November 2019 1438:Machine translation of sign languages 888:Translations by neural MT tools like 284:Internationalization and localization 7: 5393:Tasks of natural language processing 5171:Three-dimensional integrated circuit 4566:Simple Knowledge Organization System 3922:Cohen, J. M. (1986), "Translation", 3429:Translation and Interpreting Studies 3218:from the original on 21 October 2013 2282:from the original on 10 October 2015 2019:from the original on 7 February 2020 1926:from the original on 19 October 2016 1334:dictionary-based machine-translation 802:Dictionary-based machine translation 5290:Future-oriented technology analysis 5030:Progress in artificial intelligence 3476:JMIR Public Health and Surveillance 3069:Magazine, Undark (12 August 2021). 2558:Kocmi, Tom; Monz, Christof (eds.). 2374:Katsnelson, Alla (29 August 2022). 2140:Barron, Brenda (18 November 2019). 1412:in April 2017 involve two Japanese 613:The first researcher in the field, 1961:from the original on 3 August 2020 1799:Early Years in Machine Translation 1785:. Berkeley Enterprises. p. 6. 1641:ULTRA (machine translation system) 1474:. The copyright at issue is for a 1183:programs, but also in translating 764:Transfer-based machine translation 758:Transfer-based machine translation 417:Books and magazines on translation 25: 4581:Thesaurus (information retrieval) 3159:from the original on 16 June 2011 3120:Gallafent, Alex (26 April 2011). 2824:Wooten, Adam (14 February 2006). 2247:from the original on 29 June 2016 2119:. Berlin: Springer. p. 276. 2094:. New York: Elsevier. p. 5. 2092:Conceptual Information Processing 1860:from the original on 6 March 2021 1323:example-based machine translation 1309:Evaluation of machine translation 715:Example-based machine translation 5344: 3711:. Morphologic.hu. Archived from 3423:Piccoli, Vanessa (5 July 2022). 3178:Young-sil, Yoon (26 June 2023). 2805:from the original on 25 May 2011 2767:from the original on 21 May 2013 2431:Korab, Petr (18 February 2022). 2234:Multi-Source Translation Methods 2184:. Oxon: Routledge. p. 385. 1838:on 28 February 2020 – via 931:) being rendered as "wikipedia". 783:Interlingual machine translation 770:interlingual machine translation 74: 5067:Fourth-generation optical discs 3803:Bilingual Evaluation Understudy 3744:. CALICO Journal. 13(1). 68–96. 3384:10.1001/jamainternmed.2018.7653 3285:from the original on 4 May 2013 3132:from the original on 9 May 2013 2751:Neeraj Agrawal; Ankush Singla. 2005:Wolfgang Saxon (28 July 1995). 1626:Statistical machine translation 1319:statistical machine translation 820:Statistical machine translation 36:Interactive machine translation 4162:Natural language understanding 3928:, vol. 27, pp. 12–15 1723:DuPont, Quinn (January 2018). 1555:History of machine translation 945:" from machine translation in 745:Rule-based machine translation 527:History of machine translation 449:Kural translations by language 422:Bible translations by language 197:Dynamic and formal equivalence 1: 5388:Computer-assisted translation 5317:Technology in science fiction 4686:Optical character recognition 3326:10.1080/1369118X.2020.1776370 2966:"Machine Translation Service" 1646:Universal Networking Language 1581:List of emerging technologies 1526:Computer-assisted translation 1293:convolutional neural networks 501:Early approaches were mostly 437:List of most translated works 238:Translation management system 32:Computer-assisted translation 4379:Multi-document summarization 3936:; Somers, Harold L. (1992). 3854:– via www.youtube.com. 3643:Natural Language Engineering 1545:Foreign language writing aid 1344:means of evaluation include 1321:(SMT) typically outperforms 4709:Latent Dirichlet allocation 4681:Natural language generation 4546:Machine-readable dictionary 4541:Linguistic Linked Open Data 4116:Natural language processing 4031:Machine Translation Archive 3564:Journal of Court Innovation 3096:"List of Wikipedias - Meta" 2991:Wilson, Kyle (8 May 2019). 2170:and gave other examples too 1980:Gordin, Michael D. (2015). 1540:Controlled natural language 5414: 5322:Technology readiness level 5258:Technological unemployment 4461:Explicit semantic analysis 4210:Deep linguistic processing 3944:. London: Academic Press. 3558:Chavez, Edward L. (2008). 2401:10.1038/d41586-022-02767-9 2043:パーソナルコンピュータによる機械翻訳プログラムの制作 1881:パーソナルコンピュータによる機械翻訳プログラムの制作 1596:Neural machine translation 1435: 1306: 1181:Arabic machine translation 1044: 965: 882:neural machine translation 872:Neural machine translation 869: 817: 799: 780: 761: 742: 711:Hybrid machine translation 708: 524: 511:neural machine translation 29: 5383:Computational linguistics 5340: 5305:Technological singularity 5265:Technological convergence 4884: 4304:Word-sense disambiguation 4157:Computational linguistics 3891:. SEO Translator, citing 3655:10.1017/S1351324905003888 3599:10.1093/pnasnexus/pgad096 3532:legalj (2 January 2023). 3257:Canadian Family Physician 2614:28 September 2011 at the 2090:Schank, Roger C. (2014). 2041:上野, 俊夫 (13 August 1986). 1879:上野, 俊夫 (13 August 1986). 1560:Human language technology 1521:Computational linguistics 1408:. Two videos uploaded to 1406:their entertainment value 1171:Surveillance and military 992:World Health Organization 968:Word-sense disambiguation 941: 921: 623:Georgetown-IBM experiment 540:, a ninth-century Arabic 5077:Holographic data storage 4830:Natural Language Toolkit 4754:Pronunciation assessment 4656:Automatic identification 4486:Latent semantic analysis 4442:Distributional semantics 4327:Compound-term processing 4225:Named-entity recognition 4068:7 September 2007 at the 2575:10.18653/v1/2023.wmt-1.1 1920:"機械翻訳専用機「やまと」-コンピュータ博物館" 1754:Knowlson, James (1975). 1014:require to be resolved: 972:Syntactic disambiguation 494:text or speech from one 412:Journalistic translation 30:Not to be confused with 5270:Technological evolution 5243:Exploratory engineering 5072:3D optical data storage 5005:Artificial intelligence 4734:Automated essay scoring 4704:Document classification 4371:Automatic summarization 3961:New York Times Magazine 3733:Anderson, D.D. (1995). 3682:17 October 2011 at the 3538:Princeton Legal Journal 2791:. Benjamins.com. 1995. 2231:Schwartz, Lane (2008). 1811:10.1075/sihols.97.05hut 1157:English Knowledge (XXG) 1130:and then translate it. 928:Macrolepiota albuminosa 880:-based approach to MT, 644:however, and after the 294:Video game localization 202:Contrastive linguistics 5280:Technology forecasting 5275:Technological paradigm 5248:Proactionary principle 5166:Software-defined radio 4591:Universal Dependencies 4284:Terminology extraction 4267:Semantic decomposition 4262:Semantic role labeling 4252:Part-of-speech tagging 4220:Information extraction 4205:Coreference resolution 4195:Collocation extraction 3925:Encyclopedia Americana 3760:4 January 2018 at the 3740:4 January 2018 at the 3372:JAMA Internal Medicine 2734:4 January 2018 at the 2180:Chan, Sin-Wai (2015). 1899:): In 1959 Japan, the 1621:Round-trip translation 1448:American Sign Language 1281:client confidentiality 1053:information extraction 1021: 950: 932: 577:Rockefeller Foundation 377:Telephone interpreting 263:Multimedia translation 52: 40:Translator (computing) 5206:Disruptive innovation 4966:Emerging technologies 4352:Sentence segmentation 3970:Business and Politics 3797:22 March 2009 at the 3441:10.1075/tis.21012.pic 2662:) CS1 maint: others ( 2594:12 March 2007 at the 1945:Nye, Mary Jo (2016). 1565:Humour in translation 1340:statistical systems. 1196:hosted programs like 1134:Public administration 938: 918: 901:large language models 719:Before the advent of 685:Lernout & Hauspie 673:French Postal Service 619:Georgetown University 515:large language models 309:Software localization 289:Language localization 192:Translation criticism 121:Linguistic validation 50: 18:Automatic translation 5253:Technological change 5196:Collingridge dilemma 4993:Ambient intelligence 4804:Voice user interface 4515:datasets and corpora 4456:Document-term matrix 4309:Word-sense induction 4036:1 April 2019 at the 4024:24 June 2010 at the 3893:Zimbabwe Independent 3874:20 July 2018 at the 3753:Han et al. (2012), " 3048:Wikimedia Foundation 2868:on 28 September 2018 1651:Universal translator 1506:Cache language model 1478:; the author of the 1291:The advancements in 1212:The notable rise of 836:, the record of the 635:from 1955 to 1968." 593:University of London 304:Website localization 5398:Automation software 5373:Machine translation 5310:Technology scouting 5285:Accelerating change 5015:Machine translation 4878:machine translation 4784:Interactive fiction 4714:Pachinko allocation 4671:Speech segmentation 4627:Google Ngram Viewer 4399:Machine translation 4389:Text simplification 4384:Sentence extraction 4272:Semantic similarity 3992:10.1017/bap.2021.17 3050:. 23 September 2019 2681:Le défi des langues 2392:2022Natur.609..208K 1330:controlled language 1140:European Commission 1032:Non-standard speech 978:Yehoshua Bar-Hillel 838:European Parliament 826:statistical methods 615:Yehoshua Bar-Hillel 605:texts by computer. 488:Machine translation 371:Video relay service 228:Machine translation 187:Translation project 177:Translation studies 5327:Technology roadmap 5040:Speech recognition 5025:Mobile translation 4998:Internet of things 4794:Question answering 4666:Speech recognition 4531:Corpus linguistics 4511:Language resources 4294:Textual entailment 4277:Sentiment analysis 4063:John Hutchins 1999 3100:meta.wikimedia.org 2012:The New York Times 1704:. 23 February 2024 1636:Translation memory 1616:Pseudo-translation 1591:Mobile translation 1530:Translation memory 1274:formal proceedings 1202:Babylon translator 1165:Swedish Wikipedias 1116:mobile translation 1010:exigencies of the 951: 933: 550:frequency analysis 233:Mobile translation 53: 5360: 5359: 5179: 5178: 5149:Optical computing 4932: 4931: 4843: 4842: 4799:Virtual assistant 4724:Computer-assisted 4650: 4649: 4407:Computer-assisted 4365: 4364: 4357:Word segmentation 4319:Text segmentation 4257:Semantic analysis 4245:Syntactic parsing 4230:Ontology learning 3963:. pp. 48–52. 3934:Hutchins, W. John 3696:978-0-85142-483-5 3690:, London: Aslib. 3319:(11): 1515–1532. 2968:. 5 August 2011. 2504:Fadelli, Ingrid. 2386:(7925): 208–209. 2330:10.1613/jair.3540 2079:. pp. 81–84. 2076:Atlantic Magazine 1820:978-90-272-4586-1 1735:on 14 August 2019 1287:Ancient languages 1222:instant messaging 1214:social networking 1124:augmented reality 689:Atlantic Magazine 485: 484: 356:Untranslatability 207:Polysystem theory 16:(Redirected from 5405: 5348: 5347: 5295:Horizon scanning 5211:Ephemeralization 5127:Racetrack memory 5062:Extended reality 5057:Cybermethodology 4977: 4959: 4952: 4945: 4936: 4889:Dictionary-based 4870: 4863: 4856: 4847: 4820:Formal semantics 4769:Natural language 4676:Speech synthesis 4658:and data capture 4561:Semantic network 4536:Lexical resource 4519: 4337:Lexical analysis 4315: 4240:Semantic parsing 4109: 4102: 4095: 4086: 4003: 3985: 3964: 3955: 3943: 3929: 3909: 3908: 3906: 3904: 3885: 3879: 3865: 3856: 3855: 3848: 3842: 3841: 3830: 3824: 3823: 3820:Business Insider 3811: 3805: 3788: 3782: 3775: 3769: 3768:, Mumbai, India. 3751: 3745: 3731: 3725: 3724: 3722: 3720: 3715:on 19 April 2012 3705: 3699: 3675:Muegge (2006), " 3673: 3667: 3666: 3638: 3629: 3628: 3618: 3578: 3572: 3571: 3555: 3549: 3548: 3546: 3544: 3529: 3520: 3519: 3509: 3491: 3467: 3461: 3460: 3420: 3414: 3413: 3403: 3363: 3357: 3356: 3338: 3328: 3304: 3295: 3294: 3292: 3290: 3272: 3248: 3242: 3241: 3235: 3227: 3225: 3223: 3217: 3210: 3201: 3195: 3194: 3192: 3190: 3175: 3169: 3168: 3166: 3164: 3148: 3142: 3141: 3139: 3137: 3117: 3111: 3110: 3108: 3106: 3092: 3086: 3085: 3083: 3081: 3066: 3060: 3059: 3057: 3055: 3040: 3034: 3033: 3031: 3029: 3024:. 9 January 2019 3014: 3008: 3007: 3005: 3003: 2988: 2982: 2981: 2979: 2977: 2962: 2956: 2955: 2953: 2951: 2939:Whitney, Lance. 2936: 2930: 2929: 2927: 2925: 2910: 2904: 2903: 2901: 2899: 2884: 2878: 2877: 2875: 2873: 2867: 2861:. Archived from 2860: 2852: 2846: 2845: 2843: 2841: 2832:. Archived from 2830:T&I Business 2821: 2815: 2814: 2812: 2810: 2783: 2777: 2776: 2774: 2772: 2766: 2759: 2748: 2739: 2725: 2719: 2718: 2716: 2714: 2708: 2701: 2690: 2684: 2674: 2668: 2667: 2657: 2649: 2624: 2618: 2605: 2599: 2598:by John Hutchins 2586: 2580: 2579: 2577: 2554: 2548: 2547: 2545: 2532: 2521: 2520: 2518: 2516: 2501: 2495: 2494: 2492: 2479: 2473: 2472: 2470: 2468: 2454: 2448: 2447: 2445: 2443: 2428: 2422: 2421: 2403: 2371: 2365: 2364: 2362: 2350: 2344: 2341: 2335: 2334: 2332: 2322: 2298: 2292: 2291: 2289: 2287: 2281: 2274: 2263: 2257: 2256: 2254: 2252: 2246: 2239: 2228: 2222: 2221: 2219: 2217: 2202: 2196: 2195: 2177: 2171: 2168: 2162: 2161: 2159: 2157: 2137: 2131: 2130: 2112: 2106: 2105: 2087: 2081: 2080: 2070: 2057: 2056: 2038: 2032: 2031: 2026: 2024: 2002: 1996: 1995: 1977: 1971: 1970: 1968: 1966: 1942: 1936: 1935: 1933: 1931: 1916: 1910: 1909: 1897:Google Translate 1876: 1870: 1869: 1867: 1865: 1856:. 13 July 2020. 1850: 1844: 1843: 1840:Semantic Scholar 1837: 1831:. Archived from 1804: 1793: 1787: 1786: 1776: 1770: 1769: 1751: 1745: 1744: 1742: 1740: 1731:. Archived from 1720: 1714: 1713: 1711: 1709: 1694: 1688: 1687: 1685: 1683: 1678:. 3 October 2016 1668: 1576:Language barrier 1224:clients such as 1128:recognize speech 1069:rigid designator 944: 943: 939:Broken Chinese " 924: 923: 890:DeepL Translator 830:Canadian Hansard 796:Dictionary-based 699:Google Translate 589:Birkbeck College 477: 470: 463: 432:Translated books 382:Language barrier 299:Dub localization 78: 55: 21: 5413: 5412: 5408: 5407: 5406: 5404: 5403: 5402: 5363: 5362: 5361: 5356: 5336: 5175: 4986: 4983: 4982:Information and 4968: 4963: 4933: 4928: 4880: 4874: 4844: 4839: 4808: 4788:Syntax guessing 4770: 4763: 4749:Predictive text 4744:Grammar checker 4725: 4718: 4690: 4657: 4646: 4612:Bank of English 4595: 4523: 4514: 4505: 4436: 4393: 4361: 4313: 4215:Distant reading 4190:Argument mining 4176: 4172:Text processing 4118: 4113: 4070:Wayback Machine 4038:Wayback Machine 4026:Wayback Machine 4010: 3967: 3958: 3952: 3932: 3921: 3918: 3916:Further reading 3913: 3912: 3902: 3900: 3887: 3886: 3882: 3876:Wayback Machine 3866: 3859: 3850: 3849: 3845: 3832: 3831: 3827: 3813: 3812: 3808: 3799:Wayback Machine 3789: 3785: 3776: 3772: 3762:Wayback Machine 3752: 3748: 3742:Wayback Machine 3732: 3728: 3718: 3716: 3707: 3706: 3702: 3684:Wayback Machine 3674: 3670: 3640: 3639: 3632: 3580: 3579: 3575: 3557: 3556: 3552: 3542: 3540: 3531: 3530: 3523: 3469: 3468: 3464: 3422: 3421: 3417: 3365: 3364: 3360: 3306: 3305: 3298: 3288: 3286: 3250: 3249: 3245: 3228: 3221: 3219: 3215: 3208: 3203: 3202: 3198: 3188: 3186: 3177: 3176: 3172: 3162: 3160: 3150: 3149: 3145: 3135: 3133: 3126:PRI's the World 3119: 3118: 3114: 3104: 3102: 3094: 3093: 3089: 3079: 3077: 3075:Undark Magazine 3068: 3067: 3063: 3053: 3051: 3042: 3041: 3037: 3027: 3025: 3016: 3015: 3011: 3001: 2999: 2990: 2989: 2985: 2975: 2973: 2964: 2963: 2959: 2949: 2947: 2938: 2937: 2933: 2923: 2921: 2918:Popular Science 2912: 2911: 2907: 2897: 2895: 2886: 2885: 2881: 2871: 2869: 2865: 2858: 2854: 2853: 2849: 2839: 2837: 2836:on 16 July 2012 2823: 2822: 2818: 2808: 2806: 2799: 2785: 2784: 2780: 2770: 2768: 2764: 2757: 2750: 2749: 2742: 2736:Wayback Machine 2726: 2722: 2712: 2710: 2706: 2699: 2692: 2691: 2687: 2675: 2671: 2650: 2638: 2626: 2625: 2621: 2616:Wayback Machine 2606: 2602: 2596:Wayback Machine 2587: 2583: 2556: 2555: 2551: 2534: 2533: 2524: 2514: 2512: 2503: 2502: 2498: 2481: 2480: 2476: 2466: 2464: 2456: 2455: 2451: 2441: 2439: 2430: 2429: 2425: 2373: 2372: 2368: 2352: 2351: 2347: 2342: 2338: 2300: 2299: 2295: 2285: 2283: 2279: 2272: 2265: 2264: 2260: 2250: 2248: 2244: 2237: 2230: 2229: 2225: 2215: 2213: 2204: 2203: 2199: 2192: 2179: 2178: 2174: 2169: 2165: 2155: 2153: 2139: 2138: 2134: 2127: 2114: 2113: 2109: 2102: 2089: 2088: 2084: 2072: 2071: 2060: 2053: 2040: 2039: 2035: 2022: 2020: 2004: 2003: 1999: 1992: 1979: 1978: 1974: 1964: 1962: 1944: 1943: 1939: 1929: 1927: 1918: 1917: 1913: 1891: 1878: 1877: 1873: 1863: 1861: 1852: 1851: 1847: 1835: 1821: 1802: 1795: 1794: 1790: 1778: 1777: 1773: 1766: 1753: 1752: 1748: 1738: 1736: 1722: 1721: 1717: 1707: 1705: 1696: 1695: 1691: 1681: 1679: 1670: 1669: 1665: 1660: 1655: 1496: 1490:a translation. 1476:derivative work 1466:are subject to 1456: 1440: 1434: 1416:characters えぐ ( 1311: 1305: 1289: 1266: 1253: 1242: 1210: 1173: 1152:Knowledge (XXG) 1148: 1146:Knowledge (XXG) 1136: 1111: 1102: 1082:Transliteration 1049: 1043: 1034: 1012:target language 974: 966:Main articles: 964: 947:Bali, Indonesia 913: 897:directly prompt 874: 868: 822: 816: 804: 798: 785: 779: 766: 760: 747: 741: 717: 707: 695:Franz Josef Och 658: 656:1975 and beyond 641: 611: 534: 529: 523: 481: 387:Fan translation 366:Transliteration 156:Sense-for-sense 43: 28: 23: 22: 15: 12: 11: 5: 5411: 5409: 5401: 5400: 5395: 5390: 5385: 5380: 5375: 5365: 5364: 5358: 5357: 5355: 5354: 5341: 5338: 5337: 5335: 5334: 5329: 5324: 5319: 5314: 5313: 5312: 5307: 5302: 5297: 5292: 5287: 5277: 5272: 5267: 5262: 5261: 5260: 5250: 5245: 5240: 5239: 5238: 5233: 5228: 5223: 5213: 5208: 5203: 5198: 5193: 5187: 5185: 5181: 5180: 5177: 5176: 5174: 5173: 5168: 5163: 5162: 5161: 5151: 5146: 5145: 5144: 5139: 5134: 5129: 5124: 5119: 5114: 5109: 5104: 5099: 5094: 5086: 5081: 5080: 5079: 5074: 5064: 5059: 5054: 5049: 5044: 5043: 5042: 5037: 5032: 5027: 5022: 5020:Machine vision 5017: 5012: 5002: 5001: 5000: 4989: 4987: 4984:communications 4980: 4974: 4970: 4969: 4964: 4962: 4961: 4954: 4947: 4939: 4930: 4929: 4927: 4926: 4921: 4916: 4911: 4906: 4901: 4899:Transfer-based 4896: 4891: 4885: 4882: 4881: 4876:Approaches to 4875: 4873: 4872: 4865: 4858: 4850: 4841: 4840: 4838: 4837: 4832: 4827: 4822: 4816: 4814: 4810: 4809: 4807: 4806: 4801: 4796: 4791: 4781: 4775: 4773: 4771:user interface 4765: 4764: 4762: 4761: 4756: 4751: 4746: 4741: 4736: 4730: 4728: 4720: 4719: 4717: 4716: 4711: 4706: 4700: 4698: 4692: 4691: 4689: 4688: 4683: 4678: 4673: 4668: 4662: 4660: 4652: 4651: 4648: 4647: 4645: 4644: 4639: 4634: 4629: 4624: 4619: 4614: 4609: 4603: 4601: 4597: 4596: 4594: 4593: 4588: 4583: 4578: 4573: 4568: 4563: 4558: 4553: 4548: 4543: 4538: 4533: 4527: 4525: 4516: 4507: 4506: 4504: 4503: 4498: 4496:Word embedding 4493: 4488: 4483: 4476:Language model 4473: 4468: 4463: 4458: 4453: 4447: 4445: 4438: 4437: 4435: 4434: 4429: 4427:Transfer-based 4424: 4419: 4414: 4409: 4403: 4401: 4395: 4394: 4392: 4391: 4386: 4381: 4375: 4373: 4367: 4366: 4363: 4362: 4360: 4359: 4354: 4349: 4344: 4339: 4334: 4329: 4323: 4321: 4312: 4311: 4306: 4301: 4296: 4291: 4286: 4280: 4279: 4274: 4269: 4264: 4259: 4254: 4249: 4248: 4247: 4242: 4232: 4227: 4222: 4217: 4212: 4207: 4202: 4200:Concept mining 4197: 4192: 4186: 4184: 4178: 4177: 4175: 4174: 4169: 4164: 4159: 4154: 4153: 4152: 4147: 4137: 4132: 4126: 4124: 4120: 4119: 4114: 4112: 4111: 4104: 4097: 4089: 4083: 4082: 4077: 4072: 4060: 4055: 4045: 4028: 4016: 4009: 4008:External links 4006: 4005: 4004: 3965: 3956: 3950: 3930: 3917: 3914: 3911: 3910: 3880: 3857: 3843: 3825: 3806: 3783: 3770: 3746: 3726: 3700: 3668: 3649:(3): 295–309. 3630: 3593:(5): pgad096. 3573: 3550: 3521: 3462: 3415: 3378:(4): 580–582. 3358: 3296: 3263:(4): 382–383. 3243: 3196: 3170: 3143: 3112: 3087: 3061: 3035: 3009: 2983: 2957: 2931: 2920:. 30 July 2015 2905: 2879: 2847: 2816: 2797: 2778: 2740: 2720: 2709:on 14 May 2006 2685: 2669: 2636: 2619: 2600: 2581: 2549: 2522: 2510:techxplore.com 2496: 2474: 2462:Deutsche Welle 2449: 2423: 2366: 2345: 2336: 2293: 2258: 2223: 2197: 2190: 2172: 2163: 2132: 2125: 2107: 2100: 2082: 2058: 2051: 2033: 1997: 1990: 1972: 1937: 1911: 1889: 1871: 1845: 1819: 1788: 1771: 1764: 1746: 1715: 1689: 1662: 1661: 1659: 1656: 1654: 1653: 1648: 1643: 1638: 1633: 1628: 1623: 1618: 1613: 1608: 1603: 1598: 1593: 1588: 1583: 1578: 1573: 1568: 1562: 1557: 1552: 1547: 1542: 1537: 1532: 1523: 1518: 1513: 1508: 1503: 1497: 1495: 1492: 1455: 1452: 1436:Main article: 1433: 1430: 1365:human language 1307:Main article: 1304: 1301: 1288: 1285: 1269:Legal language 1265: 1262: 1252: 1249: 1241: 1238: 1209: 1206: 1172: 1169: 1147: 1144: 1135: 1132: 1110: 1107: 1101: 1098: 1045:Main article: 1042: 1041:Named entities 1039: 1033: 1030: 963: 962:Disambiguation 960: 912: 909: 870:Main article: 867: 864: 818:Main article: 815: 812: 800:Main article: 797: 794: 781:Main article: 778: 775: 762:Main article: 759: 756: 743:Main article: 740: 737: 706: 703: 687:'s GlobaLink. 657: 654: 640: 637: 610: 607: 598:Wireless World 562:René Descartes 533: 530: 525:Main article: 522: 519: 483: 482: 480: 479: 472: 465: 457: 454: 453: 452: 451: 446: 441: 440: 439: 429: 424: 419: 414: 409: 404: 399: 394: 391:of video games 384: 379: 374: 368: 363: 358: 350: 349: 348:Related topics 345: 344: 343: 342: 337: 332: 327: 319: 318: 314: 313: 312: 311: 306: 301: 296: 291: 286: 281: 273: 272: 268: 267: 266: 265: 260: 255: 250: 245: 240: 235: 230: 225: 217: 216: 212: 211: 210: 209: 204: 199: 194: 189: 184: 179: 171: 170: 166: 165: 164: 163: 158: 153: 148: 143: 141:Interpretation 138: 133: 128: 123: 118: 113: 108: 103: 98: 93: 85: 84: 80: 79: 71: 70: 64: 63: 26: 24: 14: 13: 10: 9: 6: 4: 3: 2: 5410: 5399: 5396: 5394: 5391: 5389: 5386: 5384: 5381: 5379: 5376: 5374: 5371: 5370: 5368: 5353: 5352: 5343: 5342: 5339: 5333: 5332:Transhumanism 5330: 5328: 5325: 5323: 5320: 5318: 5315: 5311: 5308: 5306: 5303: 5301: 5298: 5296: 5293: 5291: 5288: 5286: 5283: 5282: 5281: 5278: 5276: 5273: 5271: 5268: 5266: 5263: 5259: 5256: 5255: 5254: 5251: 5249: 5246: 5244: 5241: 5237: 5234: 5232: 5229: 5227: 5224: 5222: 5219: 5218: 5217: 5214: 5212: 5209: 5207: 5204: 5202: 5199: 5197: 5194: 5192: 5189: 5188: 5186: 5182: 5172: 5169: 5167: 5164: 5160: 5159:Chipless RFID 5157: 5156: 5155: 5152: 5150: 5147: 5143: 5140: 5138: 5135: 5133: 5130: 5128: 5125: 5123: 5120: 5118: 5115: 5113: 5110: 5108: 5105: 5103: 5100: 5098: 5095: 5093: 5090: 5089: 5087: 5085: 5082: 5078: 5075: 5073: 5070: 5069: 5068: 5065: 5063: 5060: 5058: 5055: 5053: 5050: 5048: 5045: 5041: 5038: 5036: 5033: 5031: 5028: 5026: 5023: 5021: 5018: 5016: 5013: 5011: 5008: 5007: 5006: 5003: 4999: 4996: 4995: 4994: 4991: 4990: 4988: 4985: 4978: 4975: 4971: 4967: 4960: 4955: 4953: 4948: 4946: 4941: 4940: 4937: 4925: 4922: 4920: 4917: 4915: 4912: 4910: 4909:Example-based 4907: 4905: 4902: 4900: 4897: 4895: 4892: 4890: 4887: 4886: 4883: 4879: 4871: 4866: 4864: 4859: 4857: 4852: 4851: 4848: 4836: 4833: 4831: 4828: 4826: 4825:Hallucination 4823: 4821: 4818: 4817: 4815: 4811: 4805: 4802: 4800: 4797: 4795: 4792: 4789: 4785: 4782: 4780: 4777: 4776: 4774: 4772: 4766: 4760: 4759:Spell checker 4757: 4755: 4752: 4750: 4747: 4745: 4742: 4740: 4737: 4735: 4732: 4731: 4729: 4727: 4721: 4715: 4712: 4710: 4707: 4705: 4702: 4701: 4699: 4697: 4693: 4687: 4684: 4682: 4679: 4677: 4674: 4672: 4669: 4667: 4664: 4663: 4661: 4659: 4653: 4643: 4640: 4638: 4635: 4633: 4630: 4628: 4625: 4623: 4620: 4618: 4615: 4613: 4610: 4608: 4605: 4604: 4602: 4598: 4592: 4589: 4587: 4584: 4582: 4579: 4577: 4574: 4572: 4571:Speech corpus 4569: 4567: 4564: 4562: 4559: 4557: 4554: 4552: 4551:Parallel text 4549: 4547: 4544: 4542: 4539: 4537: 4534: 4532: 4529: 4528: 4526: 4520: 4517: 4512: 4508: 4502: 4499: 4497: 4494: 4492: 4489: 4487: 4484: 4481: 4477: 4474: 4472: 4469: 4467: 4464: 4462: 4459: 4457: 4454: 4452: 4449: 4448: 4446: 4443: 4439: 4433: 4430: 4428: 4425: 4423: 4420: 4418: 4415: 4413: 4412:Example-based 4410: 4408: 4405: 4404: 4402: 4400: 4396: 4390: 4387: 4385: 4382: 4380: 4377: 4376: 4374: 4372: 4368: 4358: 4355: 4353: 4350: 4348: 4345: 4343: 4342:Text chunking 4340: 4338: 4335: 4333: 4332:Lemmatisation 4330: 4328: 4325: 4324: 4322: 4320: 4316: 4310: 4307: 4305: 4302: 4300: 4297: 4295: 4292: 4290: 4287: 4285: 4282: 4281: 4278: 4275: 4273: 4270: 4268: 4265: 4263: 4260: 4258: 4255: 4253: 4250: 4246: 4243: 4241: 4238: 4237: 4236: 4233: 4231: 4228: 4226: 4223: 4221: 4218: 4216: 4213: 4211: 4208: 4206: 4203: 4201: 4198: 4196: 4193: 4191: 4188: 4187: 4185: 4183: 4182:Text analysis 4179: 4173: 4170: 4168: 4165: 4163: 4160: 4158: 4155: 4151: 4148: 4146: 4143: 4142: 4141: 4138: 4136: 4133: 4131: 4128: 4127: 4125: 4123:General terms 4121: 4117: 4110: 4105: 4103: 4098: 4096: 4091: 4090: 4087: 4081: 4078: 4076: 4073: 4071: 4067: 4064: 4061: 4059: 4056: 4053: 4049: 4046: 4043: 4042:John Hutchins 4039: 4035: 4032: 4029: 4027: 4023: 4020: 4017: 4015: 4012: 4011: 4007: 4001: 3997: 3993: 3989: 3984: 3979: 3976:(1): 96–112. 3975: 3971: 3966: 3962: 3957: 3953: 3951:0-12-362830-X 3947: 3942: 3941: 3935: 3931: 3927: 3926: 3920: 3919: 3915: 3898: 3894: 3890: 3884: 3881: 3877: 3873: 3870: 3864: 3862: 3858: 3853: 3847: 3844: 3839: 3835: 3829: 3826: 3821: 3817: 3814:Abadi, Mark. 3810: 3807: 3804: 3800: 3796: 3793: 3787: 3784: 3780: 3774: 3771: 3767: 3763: 3759: 3756: 3750: 3747: 3743: 3739: 3736: 3730: 3727: 3714: 3710: 3704: 3701: 3697: 3693: 3689: 3685: 3681: 3678: 3672: 3669: 3664: 3660: 3656: 3652: 3648: 3644: 3637: 3635: 3631: 3626: 3622: 3617: 3612: 3608: 3604: 3600: 3596: 3592: 3588: 3584: 3577: 3574: 3569: 3565: 3561: 3554: 3551: 3539: 3535: 3528: 3526: 3522: 3517: 3513: 3508: 3503: 3499: 3495: 3490: 3489:10.2196/50814 3485: 3481: 3477: 3473: 3466: 3463: 3458: 3454: 3450: 3446: 3442: 3438: 3434: 3430: 3426: 3419: 3416: 3411: 3407: 3402: 3397: 3393: 3389: 3385: 3381: 3377: 3373: 3369: 3362: 3359: 3354: 3350: 3346: 3342: 3337: 3332: 3327: 3322: 3318: 3314: 3310: 3303: 3301: 3297: 3284: 3280: 3276: 3271: 3266: 3262: 3258: 3254: 3247: 3244: 3239: 3233: 3214: 3207: 3200: 3197: 3185: 3184:BusinessKorea 3181: 3174: 3171: 3158: 3154: 3147: 3144: 3131: 3127: 3123: 3116: 3113: 3101: 3097: 3091: 3088: 3076: 3072: 3065: 3062: 3049: 3045: 3039: 3036: 3023: 3019: 3013: 3010: 2998: 2994: 2987: 2984: 2971: 2967: 2961: 2958: 2946: 2942: 2935: 2932: 2919: 2915: 2909: 2906: 2893: 2889: 2883: 2880: 2864: 2857: 2851: 2848: 2835: 2831: 2827: 2820: 2817: 2804: 2800: 2798:9789027216144 2794: 2790: 2789: 2782: 2779: 2763: 2756: 2755: 2747: 2745: 2741: 2737: 2733: 2730: 2724: 2721: 2705: 2698: 2697: 2689: 2686: 2682: 2678: 2673: 2670: 2665: 2661: 2655: 2647: 2643: 2639: 2637:9783319213101 2633: 2629: 2623: 2620: 2617: 2613: 2610: 2604: 2601: 2597: 2593: 2590: 2585: 2582: 2576: 2571: 2567: 2563: 2562: 2553: 2550: 2544: 2539: 2531: 2529: 2527: 2523: 2511: 2507: 2500: 2497: 2491: 2486: 2478: 2475: 2463: 2459: 2453: 2450: 2438: 2434: 2427: 2424: 2419: 2415: 2411: 2407: 2402: 2397: 2393: 2389: 2385: 2381: 2377: 2370: 2367: 2361: 2356: 2349: 2346: 2340: 2337: 2331: 2326: 2321: 2316: 2312: 2308: 2304: 2297: 2294: 2278: 2271: 2270: 2262: 2259: 2243: 2236: 2235: 2227: 2224: 2211: 2207: 2201: 2198: 2193: 2191:9780415524841 2187: 2183: 2176: 2173: 2167: 2164: 2151: 2147: 2143: 2136: 2133: 2128: 2122: 2118: 2111: 2108: 2103: 2101:9781483258799 2097: 2093: 2086: 2083: 2078: 2077: 2069: 2067: 2065: 2063: 2059: 2054: 2048: 2044: 2037: 2034: 2030: 2018: 2014: 2013: 2008: 2001: 1998: 1993: 1991:9780226000299 1987: 1983: 1976: 1973: 1960: 1956: 1952: 1951:Distillations 1948: 1941: 1938: 1925: 1921: 1915: 1912: 1908: 1906: 1902: 1898: 1892: 1886: 1882: 1875: 1872: 1859: 1855: 1849: 1846: 1841: 1834: 1830: 1826: 1822: 1816: 1812: 1808: 1801: 1800: 1792: 1789: 1784: 1783: 1775: 1772: 1767: 1765:0-8020-5296-7 1761: 1757: 1750: 1747: 1734: 1730: 1726: 1719: 1716: 1703: 1699: 1693: 1690: 1677: 1676:IEEE Spectrum 1673: 1667: 1664: 1657: 1652: 1649: 1647: 1644: 1642: 1639: 1637: 1634: 1632: 1629: 1627: 1624: 1622: 1619: 1617: 1614: 1612: 1609: 1607: 1604: 1602: 1599: 1597: 1594: 1592: 1589: 1587: 1584: 1582: 1579: 1577: 1574: 1572: 1569: 1566: 1563: 1561: 1558: 1556: 1553: 1551: 1548: 1546: 1543: 1541: 1538: 1536: 1533: 1531: 1527: 1524: 1522: 1519: 1517: 1514: 1512: 1509: 1507: 1504: 1502: 1499: 1498: 1493: 1491: 1489: 1485: 1481: 1480:original work 1477: 1473: 1469: 1465: 1461: 1453: 1451: 1449: 1444: 1439: 1431: 1429: 1427: 1426: 1421: 1420: 1415: 1411: 1407: 1402: 1398: 1396: 1391: 1387: 1383: 1379: 1375: 1370: 1366: 1361: 1359: 1355: 1351: 1347: 1343: 1337: 1335: 1331: 1326: 1324: 1320: 1315: 1310: 1302: 1300: 1298: 1294: 1286: 1284: 1282: 1277: 1275: 1270: 1263: 1261: 1257: 1250: 1248: 1246: 1239: 1237: 1235: 1234:MSN Messenger 1231: 1227: 1223: 1219: 1215: 1207: 1205: 1203: 1199: 1195: 1190: 1186: 1182: 1178: 1170: 1168: 1166: 1162: 1158: 1153: 1145: 1143: 1141: 1133: 1131: 1129: 1125: 1120: 1117: 1108: 1106: 1099: 1097: 1095: 1089: 1086: 1083: 1079: 1077: 1072: 1070: 1065: 1061: 1056: 1054: 1048: 1040: 1038: 1031: 1029: 1026: 1020: 1015: 1013: 1009: 1005: 1001: 997: 993: 989: 985: 981: 979: 973: 969: 961: 959: 956: 948: 937: 930: 929: 917: 910: 908: 906: 902: 898: 893: 891: 886: 883: 879: 878:deep learning 873: 865: 863: 861: 856: 854: 849: 847: 843: 839: 835: 831: 827: 821: 813: 811: 809: 803: 795: 793: 791: 784: 776: 774: 771: 765: 757: 755: 752: 746: 738: 736: 735:annotations. 734: 730: 726: 725:morphological 722: 721:deep learning 716: 712: 704: 702: 700: 696: 692: 690: 686: 680: 677: 674: 670: 666: 665:computational 662: 655: 653: 649: 647: 638: 636: 634: 630: 629:David G. Hays 626: 624: 620: 616: 608: 606: 604: 600: 599: 594: 590: 586: 582: 581:Warren Weaver 578: 574: 573:Warren Weaver 570: 565: 563: 559: 555: 551: 547: 546:cryptanalysis 543: 542:cryptographer 539: 531: 528: 520: 518: 516: 512: 508: 504: 499: 497: 493: 489: 478: 473: 471: 466: 464: 459: 458: 456: 455: 450: 447: 445: 442: 438: 435: 434: 433: 430: 428: 425: 423: 420: 418: 415: 413: 410: 408: 405: 403: 400: 398: 395: 392: 388: 385: 383: 380: 378: 375: 372: 369: 367: 364: 362: 361:Transcription 359: 357: 354: 353: 352: 351: 346: 341: 338: 336: 335:Organizations 333: 331: 328: 326: 323: 322: 321: 320: 317:Institutional 315: 310: 307: 305: 302: 300: 297: 295: 292: 290: 287: 285: 282: 280: 279:Glocalization 277: 276: 275: 274: 269: 264: 261: 259: 256: 254: 251: 249: 246: 244: 241: 239: 236: 234: 231: 229: 226: 224: 221: 220: 219: 218: 213: 208: 205: 203: 200: 198: 195: 193: 190: 188: 185: 183: 182:Skopos theory 180: 178: 175: 174: 173: 172: 167: 162: 159: 157: 154: 152: 151:Word-for-word 149: 147: 144: 142: 139: 137: 134: 132: 129: 127: 124: 122: 119: 117: 114: 112: 109: 107: 104: 102: 101:Bhagavad-gita 99: 97: 94: 92: 89: 88: 87: 86: 81: 77: 73: 72: 69: 65: 61: 57: 56: 49: 45: 41: 37: 33: 19: 5349: 5236:Robot ethics 5035:Semantic Web 5014: 4914:Interlingual 4877: 4739:Concordancer 4398: 4135:Bag-of-words 3973: 3969: 3960: 3939: 3924: 3901:. Retrieved 3883: 3846: 3837: 3828: 3819: 3809: 3786: 3773: 3765: 3749: 3729: 3717:. Retrieved 3713:the original 3703: 3687: 3671: 3646: 3642: 3590: 3586: 3576: 3567: 3563: 3553: 3541:. Retrieved 3537: 3479: 3475: 3465: 3435:(1): 42–65. 3432: 3428: 3418: 3375: 3371: 3361: 3316: 3312: 3287:. Retrieved 3260: 3256: 3246: 3220:. Retrieved 3199: 3187:. Retrieved 3183: 3173: 3161:. Retrieved 3146: 3136:17 September 3134:. Retrieved 3125: 3115: 3103:. Retrieved 3099: 3090: 3078:. Retrieved 3074: 3064: 3052:. Retrieved 3047: 3038: 3026:. Retrieved 3021: 3012: 3000:. Retrieved 2996: 2986: 2976:13 September 2974:. Retrieved 2960: 2948:. Retrieved 2944: 2934: 2922:. Retrieved 2917: 2908: 2896:. Retrieved 2882: 2870:. Retrieved 2863:the original 2850: 2838:. Retrieved 2834:the original 2829: 2819: 2807:. Retrieved 2787: 2781: 2769:. Retrieved 2753: 2723: 2711:. Retrieved 2704:the original 2695: 2688: 2680: 2677:Claude Piron 2672: 2627: 2622: 2603: 2584: 2565: 2560: 2552: 2513:. Retrieved 2509: 2499: 2477: 2465:. Retrieved 2461: 2452: 2440:. Retrieved 2436: 2426: 2383: 2379: 2369: 2348: 2339: 2310: 2306: 2296: 2284:. Retrieved 2268: 2261: 2249:. Retrieved 2233: 2226: 2214:. Retrieved 2200: 2181: 2175: 2166: 2154:. Retrieved 2145: 2135: 2116: 2110: 2091: 2085: 2074: 2042: 2036: 2028: 2021:. Retrieved 2010: 2000: 1981: 1975: 1963:. Retrieved 1957:(1): 40–43. 1954: 1950: 1940: 1928:. Retrieved 1914: 1904: 1894: 1880: 1874: 1862:. Retrieved 1848: 1833:the original 1798: 1791: 1781: 1774: 1755: 1749: 1737:. Retrieved 1733:the original 1728: 1718: 1706:. Retrieved 1701: 1692: 1680:. Retrieved 1675: 1666: 1457: 1445: 1441: 1423: 1417: 1403: 1399: 1384:, which the 1374:Claude Piron 1362: 1338: 1327: 1316: 1312: 1290: 1278: 1267: 1258: 1254: 1243: 1240:Online games 1211: 1208:Social media 1174: 1149: 1137: 1121: 1112: 1103: 1100:Applications 1090: 1087: 1080: 1073: 1063: 1059: 1057: 1050: 1047:Named entity 1035: 1022: 1017: 1002:, which the 988:Claude Piron 986: 982: 975: 952: 926: 894: 887: 875: 857: 852: 850: 823: 805: 786: 777:Interlingual 767: 751:dictionaries 748: 718: 693: 688: 681: 678: 659: 650: 646:ALPAC report 642: 627: 612: 596: 566: 535: 500: 487: 486: 325:Associations 271:Localization 227: 215:Technologies 44: 5300:Moore's law 5231:Neuroethics 5226:Cyberethics 5047:Atomtronics 4904:Statistical 4696:Topic model 4576:Text corpus 4422:Statistical 4289:Text mining 4130:AI-complete 3903:24 November 3232:cite report 3155:. Gcn.com. 3022:VentureBeat 2515:18 December 2313:: 179–222. 2156:22 November 2146:Digital.com 1739:2 September 1611:Postediting 1606:Phraselator 1567:("howlers") 1501:AI-complete 1395:meaningless 1386:grammatical 1382:source text 1378:ambiguities 1230:Google Talk 1004:grammatical 1000:source text 996:ambiguities 899:generative 814:Statistical 790:interlingua 587:machine at 569:A. D. Booth 554:probability 507:statistical 444:Translators 258:Postediting 253:Pre-editing 68:Translation 5367:Categories 5191:Automation 4894:Rule-based 4417:Rule-based 4299:Truecasing 4167:Stop words 3983:2011.01007 3779:techniques 3587:PNAS Nexus 3543:4 December 3482:: e50814. 3289:21 October 3222:21 October 3054:10 January 2771:4 November 2713:4 November 2543:2210.14250 2490:2302.09210 2360:1906.09833 2286:3 February 2251:3 November 2126:3540652590 2052:494762700X 1890:494762700X 1472:creativity 1303:Evaluation 808:dictionary 739:Rule-based 709:See also: 705:Approaches 558:statistics 503:rule-based 407:Scanlation 248:Subtitling 161:Homophonic 131:Regulatory 5221:Bioethics 5107:Millipede 4726:reviewing 4524:standards 4522:Types and 4000:226236853 3607:2752-6542 3498:2369-2960 3457:246780731 3449:1932-2798 3392:2168-6106 3353:225694304 3345:1369-118X 3105:9 January 3080:9 January 3028:9 January 3002:9 January 2997:The Verge 2950:9 January 2924:9 January 2654:cite book 2646:953581497 2467:9 January 2442:9 January 2418:251931306 2320:1401.6876 1829:163460375 1601:OpenLogos 1468:copyright 1462:that are 1454:Copyright 1342:Automated 1245:Lineage W 1064:Fabrionix 866:Neural MT 729:syntactic 639:1960–1975 492:translate 136:Technical 5142:UltraRAM 4642:Wikidata 4622:FrameNet 4607:BabelNet 4586:Treebank 4556:PropBank 4501:Word2vec 4466:fastText 4347:Stemming 4066:Archived 4034:Archived 4022:Archived 3897:Archived 3872:Archived 3795:Archived 3790:See the 3758:Archived 3738:Archived 3680:Archived 3625:37143863 3616:10153418 3516:37983078 3507:10696499 3410:30801626 3283:Archived 3279:23585608 3213:Archived 3189:8 August 3157:Archived 3130:Archived 2970:Archived 2892:Archived 2803:Archived 2762:Archived 2732:Archived 2612:Archived 2592:Archived 2410:36038730 2277:Archived 2242:Archived 2210:Archived 2150:Archived 2023:7 August 2017:Archived 1965:20 March 1959:Archived 1924:Archived 1864:7 August 1858:Archived 1702:PCMag UK 1494:See also 1464:original 1414:hiragana 1297:Akkadian 1251:Medicine 1218:Facebook 834:EUROPARL 733:semantic 538:Al-Kindi 496:language 146:Cultural 96:Literary 60:a series 58:Part of 5088:Memory 4813:Related 4779:Chatbot 4637:WordNet 4617:DBpedia 4491:Seq2seq 4235:Parsing 4150:Trigram 3719:12 June 3663:3242163 3401:6450297 3270:3625087 3163:12 June 2898:12 June 2872:12 June 2840:12 June 2809:12 June 2388:Bibcode 2216:12 June 1930:4 April 1729:Amodern 1488:publish 1410:YouTube 1390:lexical 1380:in the 1369:context 1008:lexical 998:in the 860:corpora 842:CANDIDE 661:SYSTRAN 603:Braille 532:Origins 521:History 340:Schools 243:Dubbing 126:Medical 5216:Ethics 5184:Topics 4973:Fields 4924:Hybrid 4919:Neural 4786:(c.f. 4444:models 4432:Neural 4145:Bigram 4140:n-gram 3998: 3948: 3764:," in 3694: 3686:," in 3661: 3623: 3613: 3605: 3570:: 303. 3514: 3504: 3496: 3455: 3447: 3408: 3398: 3390: 3351: 3343: 3277: 3267: 2795: 2644: 2634: 2437:Medium 2416: 2408: 2380:Nature 2188: 2123: 2098: 2049: 1988: 1905:Yamato 1887: 1827: 1817: 1762: 1708:7 July 1682:7 July 1484:rights 1356:, and 1354:METEOR 1185:Pashto 1161:German 1109:Travel 911:Issues 731:, and 552:, and 402:Fandub 397:Fansub 330:Awards 169:Theory 5137:SONOS 5097:ECRAM 5092:CBRAM 5084:GPGPU 4835:spaCy 4480:large 4471:GloVe 3996:S2CID 3978:arXiv 3659:S2CID 3453:S2CID 3349:S2CID 3216:(PDF) 3209:(PDF) 2866:(PDF) 2859:(PDF) 2765:(PDF) 2758:(PDF) 2707:(PDF) 2700:(PDF) 2538:arXiv 2485:arXiv 2414:S2CID 2355:arXiv 2315:arXiv 2280:(PDF) 2273:(PDF) 2245:(PDF) 2238:(PDF) 1836:(PDF) 1825:S2CID 1803:(PDF) 1658:Notes 1460:works 1458:Only 1358:LEPOR 1226:Skype 1220:, or 1198:TIDES 1194:DARPA 1060:Smith 903:like 844:from 609:1950s 585:APEXC 373:(VRS) 116:Kural 111:Quran 106:Bible 91:Legal 83:Types 38:, or 5351:List 5154:RFID 5132:RRAM 5122:PRAM 5117:NRAM 5112:MRAM 5102:FRAM 4600:Data 4451:BERT 4052:PDFs 3946:ISBN 3905:2012 3852:"えぐ" 3838:ねとらぼ 3801:and 3721:2012 3692:ISBN 3621:PMID 3603:ISSN 3545:2023 3512:PMID 3494:ISSN 3445:ISSN 3406:PMID 3388:ISSN 3341:ISSN 3291:2013 3275:PMID 3238:link 3224:2013 3191:2023 3165:2012 3138:2013 3107:2023 3082:2023 3056:2023 3030:2023 3004:2023 2978:2013 2952:2023 2945:CNET 2926:2023 2900:2012 2874:2012 2842:2012 2811:2012 2793:ISBN 2773:2013 2715:2013 2664:link 2660:link 2642:OCLC 2632:ISBN 2517:2022 2469:2023 2444:2023 2406:PMID 2288:2015 2253:2017 2218:2012 2186:ISBN 2158:2019 2121:ISBN 2096:ISBN 2047:ISBN 2025:2020 1986:ISBN 1967:2018 1932:2017 1885:ISBN 1866:2020 1815:ISBN 1760:ISBN 1741:2019 1710:2024 1684:2024 1528:and 1422:and 1388:and 1350:NIST 1346:BLEU 1332:, a 1200:and 1189:Dari 1187:and 1177:9-11 1163:and 1094:BLEU 1076:BLEU 1062:and 1006:and 970:and 942:沒有進入 853:into 713:and 633:Rand 571:and 556:and 513:and 4632:UBY 4040:by 3988:doi 3651:doi 3611:PMC 3595:doi 3502:PMC 3484:doi 3437:doi 3396:PMC 3380:doi 3376:179 3331:hdl 3321:doi 3265:PMC 2570:doi 2396:doi 2384:609 2325:doi 1807:doi 1264:Law 1051:In 925:" ( 905:GPT 846:IBM 575:at 505:or 223:CAT 5369:: 3994:. 3986:. 3974:24 3972:. 3895:. 3860:^ 3836:. 3818:. 3657:. 3647:11 3645:. 3633:^ 3619:. 3609:. 3601:. 3589:. 3585:. 3566:. 3562:. 3536:. 3524:^ 3510:. 3500:. 3492:. 3478:. 3474:. 3451:. 3443:. 3433:17 3431:. 3427:. 3404:. 3394:. 3386:. 3374:. 3370:. 3347:. 3339:. 3329:. 3317:24 3315:. 3311:. 3299:^ 3281:. 3273:. 3261:59 3259:. 3255:. 3234:}} 3230:{{ 3182:. 3128:. 3124:. 3098:. 3073:. 3046:. 3020:. 2995:. 2943:. 2916:. 2828:. 2801:. 2760:. 2743:^ 2679:, 2656:}} 2652:{{ 2640:. 2564:. 2525:^ 2508:. 2460:. 2435:. 2412:. 2404:. 2394:. 2382:. 2378:. 2323:. 2311:44 2309:. 2305:. 2148:. 2144:. 2061:^ 2027:. 2015:. 2009:. 1953:. 1949:. 1922:. 1893:. 1823:. 1813:. 1727:. 1700:. 1674:. 1425:gu 1397:. 1360:. 1352:, 1348:, 1276:. 1232:, 1228:, 1025:AI 922:鸡枞 876:A 727:, 548:, 517:. 62:on 34:, 4958:e 4951:t 4944:v 4869:e 4862:t 4855:v 4790:) 4513:, 4482:) 4478:( 4108:e 4101:t 4094:v 4002:. 3990:: 3980:: 3954:. 3907:. 3840:. 3822:. 3723:. 3698:. 3665:. 3653:: 3627:. 3597:: 3591:2 3568:1 3547:. 3518:. 3486:: 3480:9 3459:. 3439:: 3412:. 3382:: 3355:. 3333:: 3323:: 3293:. 3240:) 3226:. 3193:. 3167:. 3140:. 3109:. 3084:. 3058:. 3032:. 3006:. 2980:. 2954:. 2928:. 2902:. 2876:. 2844:. 2813:. 2775:. 2717:. 2666:) 2648:. 2578:. 2572:: 2546:. 2540:: 2519:. 2493:. 2487:: 2471:. 2446:. 2420:. 2398:: 2390:: 2363:. 2357:: 2333:. 2327:: 2317:: 2290:. 2255:. 2220:. 2194:. 2160:. 2129:. 2104:. 2055:. 1994:. 1969:. 1955:2 1934:. 1868:. 1842:. 1809:: 1768:. 1743:. 1712:. 1686:. 1419:e 591:( 476:e 469:t 462:v 393:) 389:( 42:. 20:)

Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.

Index