205:
184:
156:
90:
80:
53:
22:
609:
GPT-2 is not a recurrent neural network, but rather based on
Transformer attention based architecture. Would be nice if somebody provided truthfull critical view, because there are plenty of issues in the idea of posing language learning as pure statistical problem. There is real danger that common
540:
The section on unigram models is needlessly complicated: these are simple
Bernoulli models, there is no need to bring in Finite State Automata at all. But before removing the unnecessary complexity I'd like to ask if anybody recalls why it was put there in the first place, maybe I'm missing
457:
Recent changes in the page have replaced the word "neural" (as in "neural net language models") to "neuronal", saying that the latter is the adjective form of "neuron". While that might be true, the change is completely wrong on several accounts:
476:
I do not wish to start an edit war, so I would like to ask the editors to step in and change "neuronal" back to "neural". As I understand, WP aims to be an impartial encyclopedia, and certainly, using the established terms is part of that.
255:
633:, but rather involve a language component (including text-to speech and text-to-image models). I'm removing these, and will probably merge the contents with the table at
686:
399:
395:
381:
681:
676:
136:
146:
701:
245:
691:
165:
63:
706:
112:
671:
221:
696:
611:
591:
572:
506:
486:
556:
278:
472:
Even in biology, where the inspiration comes from, the network is called neural. That it is made up of neurons is a secondary detail.
377:
When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.
103:
58:
641:
212:
189:
645:
331:
442:
33:
610:
people will missinterpret the output of such models as it happens with almost every other deep learning architecture.
367:
466:
398:
to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the
315:
Isnt the term language models in
Information Retrieval used a little differently from the NLP interpretation?
615:
595:
576:
521:), are not covered in the article's text. Could anybody cover them accordingly please? Thank you in advace, --
295:
can also be used as a language model, and its performance is said to be worse than n-gram, though I doubt it.
490:
433:
359:
282:
629:
The "notable language models" section currently contains a number of models which are not language models
552:
526:
355:
510:
417:
If you have discovered URLs which were erroneously considered dead by the bot, you can report them with
405:
39:
548:
358:. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit
204:
183:
634:
544:
514:
482:
319:
21:
220:
on
Knowledge. If you would like to participate, please visit the project page, where you can join
111:
on
Knowledge. If you would like to participate, please visit the project page, where you can join
327:
95:
402:
before doing mass systematic removals. This message is updated dynamically through the template
418:
653:
522:
425:
469:. The change to "neuronal" here is inconsistent with the wording there or elsewhere on WP.
384:, "External links modified" talk page sections are no longer generated or monitored by
351:
300:
424:
If you found an error with any archives or the URLs themselves, you can fix them with
155:
665:
323:
368:
https://web.archive.org/web/20120302151523/http://www-speech.sri.com/projects/srilm/
649:
391:
108:
89:
390:. No special action is required regarding these talk page notices, other than
217:
85:
296:
371:
657:
619:
599:
580:
560:
530:
494:
447:
335:
304:
286:
79:
52:
462:
The generally accepted term is "neural net". Nobody uses "neuronal".
637:, since the list doesn't seem to include any LMs that aren't LLMs.
642:
here's a permalink to the section as it existed before I gutted it
518:
644:. It might be useful if someone ever wants to create a list like
292:
15:
154:
362:
for additional information. I made the following changes:
277:
what about non statistical language models, like cfgs?
216:, a collaborative effort to improve the coverage of
107:, a collaborative effort to improve the coverage of
394:using the archive tool instructions below. Editors
625:Trimming/merging list of language models section
380:This message was posted before February 2018.
8:
509:model, as well as models based on it (e.g.
646:List of natural language processing models
480:
350:I have just modified one external link on
178:
47:
372:http://www-speech.sri.com/projects/srilm
687:Applied Linguistics Task Force articles
180:
49:
19:
7:
682:C-Class applied linguistics articles
677:High-importance Linguistics articles
210:This article is within the scope of
101:This article is within the scope of
567:Erick is the best teacher in njombe
501:Transformer, and models based on it
38:It is of interest to the following
702:Low-importance Statistics articles
14:
354:. Please take a moment to review
121:Knowledge:WikiProject Linguistics
692:WikiProject Linguistics articles
230:Knowledge:WikiProject Statistics
203:
182:
124:Template:WikiProject Linguistics
88:
78:
51:
20:
707:WikiProject Statistics articles
605:Criticism section is misleading
273:Non statistical language models
250:This article has been rated as
233:Template:WikiProject Statistics
141:This article has been rated as
166:Applied Linguistics Task Force
1:
600:13:25, 14 December 2022 (UTC)
495:09:51, 27 February 2020 (UTC)
448:22:05, 16 December 2017 (UTC)
224:and see a list of open tasks.
163:This article is supported by
115:and see a list of open tasks.
672:C-Class Linguistics articles
581:15:45, 2 November 2022 (UTC)
531:20:31, 1 November 2020 (UTC)
453:"Neuronal" language models?!
305:00:18, 29 January 2009 (UTC)
287:20:44, 7 December 2008 (UTC)
697:C-Class Statistics articles
620:21:10, 5 January 2023 (UTC)
467:"Artificial neural network"
465:The WP page is also titled
723:
561:21:44, 16 March 2022 (UTC)
536:Unigram models -- why FSA?
411:(last update: 5 June 2024)
347:Hello fellow Wikipedians,
147:project's importance scale
658:18:24, 9 March 2023 (UTC)
336:16:16, 1 March 2011 (UTC)
249:
198:
162:
140:
73:
46:
505:Non-RNN attention-based
343:External links modified
104:WikiProject Linguistics
213:WikiProject Statistics
159:
28:This article is rated
158:
635:Large language model
392:regular verification
127:Linguistics articles
382:After February 2018
236:Statistics articles
64:Applied Linguistics
571:Erick is the best
436:InternetArchiveBot
387:InternetArchiveBot
160:
96:Linguistics portal
34:content assessment
547:comment added by
497:
485:comment added by
412:
339:
322:comment added by
270:
269:
266:
265:
262:
261:
177:
176:
173:
172:
714:
590:I ned story I’m
563:
446:
437:
410:
409:
388:
338:
316:
256:importance scale
238:
237:
234:
231:
228:
207:
200:
199:
194:
186:
179:
129:
128:
125:
122:
119:
98:
93:
92:
82:
75:
74:
69:
66:
55:
48:
31:
25:
24:
16:
722:
721:
717:
716:
715:
713:
712:
711:
662:
661:
640:For posterity,
627:
607:
588:
569:
542:
538:
503:
455:
440:
435:
403:
396:have permission
386:
360:this simple FaQ
345:
317:
313:
311:Language Models
275:
235:
232:
229:
226:
225:
192:
143:High-importance
126:
123:
120:
117:
116:
94:
87:
68:High‑importance
67:
61:
32:on Knowledge's
29:
12:
11:
5:
720:
718:
710:
709:
704:
699:
694:
689:
684:
679:
674:
664:
663:
648:or something.
626:
623:
612:31.182.202.212
606:
603:
592:94.249.104.173
587:
584:
573:197.250.225.87
568:
565:
537:
534:
502:
499:
474:
473:
470:
463:
454:
451:
430:
429:
422:
375:
374:
366:Added archive
352:Language model
344:
341:
312:
309:
308:
307:
274:
271:
268:
267:
264:
263:
260:
259:
252:Low-importance
248:
242:
241:
239:
222:the discussion
208:
196:
195:
193:Low‑importance
187:
175:
174:
171:
170:
161:
151:
150:
139:
133:
132:
130:
113:the discussion
100:
99:
83:
71:
70:
56:
44:
43:
37:
26:
13:
10:
9:
6:
4:
3:
2:
719:
708:
705:
703:
700:
698:
695:
693:
690:
688:
685:
683:
680:
678:
675:
673:
670:
669:
667:
660:
659:
655:
651:
647:
643:
638:
636:
632:
624:
622:
621:
617:
613:
604:
602:
601:
597:
593:
585:
583:
582:
578:
574:
566:
564:
562:
558:
554:
550:
546:
535:
533:
532:
528:
524:
520:
516:
512:
508:
500:
498:
496:
492:
488:
487:176.63.22.138
484:
478:
471:
468:
464:
461:
460:
459:
452:
450:
449:
444:
439:
438:
427:
423:
420:
416:
415:
414:
407:
401:
397:
393:
389:
383:
378:
373:
369:
365:
364:
363:
361:
357:
353:
348:
342:
340:
337:
333:
329:
325:
321:
310:
306:
302:
298:
294:
291:
290:
289:
288:
284:
280:
272:
257:
253:
247:
244:
243:
240:
223:
219:
215:
214:
209:
206:
202:
201:
197:
191:
188:
185:
181:
168:
167:
157:
153:
152:
148:
144:
138:
135:
134:
131:
114:
110:
106:
105:
97:
91:
86:
84:
81:
77:
76:
72:
65:
60:
57:
54:
50:
45:
41:
35:
27:
23:
18:
17:
639:
630:
628:
608:
589:
570:
549:SnoTraveller
543:— Preceding
541:something.
539:
523:Olexa Riznyk
504:
481:— Preceding
479:
475:
456:
434:
431:
406:source check
385:
379:
376:
349:
346:
318:— Preceding
314:
279:84.162.237.4
276:
251:
211:
164:
142:
102:
40:WikiProjects
507:Transformer
118:Linguistics
109:linguistics
59:Linguistics
666:Categories
443:Report bug
227:Statistics
218:statistics
190:Statistics
426:this tool
419:this tool
557:contribs
545:unsigned
483:unsigned
432:Cheers.—
332:contribs
324:GreenEdu
320:unsigned
650:Colin M
356:my edit
254:on the
145:on the
30:C-class
631:per se
36:scale.
519:GPT-3
654:talk
616:talk
596:talk
577:talk
553:talk
527:talk
511:BERT
491:talk
328:talk
301:talk
297:Took
293:PCFG
283:talk
137:High
515:GPT
400:RfC
370:to
246:Low
668::
656:)
618:)
598:)
586:Hi
579:)
559:)
555:•
529:)
517:,
513:,
493:)
413:.
408:}}
404:{{
334:)
330:•
303:)
285:)
62::
652:(
614:(
594:(
575:(
551:(
525:(
489:(
445:)
441:(
428:.
421:.
326:(
299:(
281:(
258:.
169:.
149:.
42::
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.