156:, even where the lower court's decision contains more discussion of the relevant facts. The opposite may be true, however, if the senior court has only a minor discussion of the topic (for example, if it is a secondary consideration in the case). An information retrieval system must also be aware of the authority of the jurisdiction. A case from a binding authority is most likely of more value than one from a non-binding authority.
34:, and scholarly works. Accurate legal information retrieval is important to provide access to the law to laymen and legal professionals. Its importance has increased because of the vast and quickly increasing amount of legal documents available through electronic means. Legal information retrieval is a part of the growing field of
210:' Headnote searches. Additionally, both of these services allow browsing of their classifications, via Westlaw's West Key Numbers or Lexis' Headnotes. Though these two search algorithms are proprietary and secret, it is known that they employ manual classification of text (though this may be computer-assisted).
159:
Additionally, the intentions of the user may determine which cases they find valuable. For instance, where a legal professional is attempting to argue a specific interpretation of law, he might find a minor court's decision which supports his position more valuable than a senior courts position which
114:
must also be programmed to deal with law-specific words and phrases. Though this is less problematic in the context of words which exist solely in law, legal texts also frequently use polysemes, words may have different meanings when used in a legal or common-speech manner, potentially both within
226:
In order to reduce the reliance on legal professionals and the amount of time needed, efforts have been made to create a system to automatically classify legal text and queries. Adequate translation of both would allow accurate information retrieval without the high cost of human classification.
563:
Loui, R. P., Norman, J., Altepeter, J., Pinkard, D., Craven, D., Linsday, J., & Foltz, M. (1997, June). Progress on Room 5: A testbed for public interactive semi-formal legal argumentation. In
Proceedings of the 6th international conference on Artificial intelligence and law (pp. 207-214).
213:
These systems can help overcome the majority of problems inherent in legal information retrieval systems, in that manual classification has the greatest chances of identifying landmark cases and understanding the issues that arise in the text. In one study, ontological searching resulted in a
163:
Overcoming these problems can be made more difficult because of the large number of cases available. The number of legal cases available via electronic means is constantly increasing (in 2003, US appellate courts handed down approximately 500 new cases per day), meaning that an accurate legal
187:
to be roughly 20%, and its precision rate to be roughly 79%. Another study implemented a generic search (that is, not designed for legal uses) and found a recall rate of 56% and a precision rate of 72% among legal professionals. Both numbers increased when searches were run by non-legal
217:
The major drawback to this approach is the requirement of using highly skilled legal professionals and large amounts of time to classify texts. As the amount of text available continues to increase, some have stated their belief that manual classification is unsustainable.
201:
to classify the texts, based on the way a legal professional might think about them. These attempt to link texts on the basis of their type, their value, and/or their topic areas. Most major legal search providers now implement some sort of classification search, such as
180:, where a user may specify terms such as use of specific words or judgments by a specific court, are the most common type of search available via legal information retrieval systems. They are widely implemented but overcome few of the problems discussed above.
147:
Even if a system overcomes the language problems inherent in law, it must still determine the relevancy of each result. In the context of judicial decisions, this requires determining the precedential value of the case. Case decisions from senior or
49:
as low as 20 percent, meaning that only 1 in 5 relevant documents are actually retrieved. In that case, researchers believed that they had retrieved over 75% of relevant documents. This may result in failing to retrieve important or
196:
In order to overcome the limits of basic boolean searches, information systems have attempted to classify case laws and statutes into more computer friendly structures. Usually, this results in the creation of an
115:
the same document. The legal meanings may be dependent on the area of law in which it is applied. For example, in the context of
European Union legislation, the term "worker" has four different meanings:
129:
Any person carrying out an occupation on board a vessel, including trainees and apprentices, but excluding port pilots and shore personnel carrying out work on board a vessel at the quayside;
214:
precision rate of 82% and a recall rate of 97% among legal professionals. The legal texts included, however, were carefully controlled to just a few areas of law in a specific jurisdiction.
235:. Though multiple systems have been postulated, few have reported results. One system, “SMILE,” which attempted to automatically extract classifications from case texts, resulted in an
239:(which is a calculation of both recall rate and precision) of under 0.3 (compared to perfect f-measure of 1.0). This is probably much lower than an acceptable rate for general usage.
250:
In the mid-90s the Room 5 case law retrieval project used citation mining for summaries and ranked its search results based on citation type and count. This slightly pre-dated the
144:
Though the terms may be similar, correct information retrieval must differentiate between the intended use and irrelevant uses in order to return the correct results.
759:
Schweighofer, E.; Liebwald, D. (2007). "Advanced lexical ontologies and hybrid knowledge based systems: First steps to a dynamic legal electronic commentary".
188:
professionals, to a 68% recall rate and 77% precision rate. This is likely explained because of the use of complex legal terms by the legal professionals.
183:
The recall and precision rates of these searches vary depending on the implementation and searches analyzed. One study found a basic boolean search's
61:
Legal
Information Retrieval attempts to increase the effectiveness of legal searches by increasing the number of relevant documents (providing a high
132:
Any person who, in the Member State concerned, is protected as an employee under national employment law and in accordance with national practice;
254:
algorithm at
Stanford which was also a citation-based ranking. Ranking of results was based as much on jurisdiction as on number of references.
242:
Despite the limited results, many theorists predict that the evolution of such systems will eventually replace manual classification systems.
874:
879:
100:
techniques to legal text can be more difficult than application in other subjects. One key problem is that the law rarely has an inherent
805:
628:
859:
41:
In a legal setting, it is frequently important to retrieve all information related to a specific query. However, commonly used
160:
does not. He may also value similar positions from different areas of law, different jurisdictions, or dissenting opinions.
889:
104:. Instead, the law is generally filled with open-ended terms, which may change over time. This can be especially true in
228:
85:
652:
Blair, D.C.; Maron, M.E. (1985). "An evaluation of retrieval effectiveness for a full-text document-retrieval".
884:
730:
Saravanan, M.; et al. (2007). "Improving legal information retrieval using an ontological framework".
605:"Information extraction from case law and retrieval of prior cases by partial parsing and query generation"
45:
methods (exact matches of specified terms) on full text legal documents have been shown to have an average
700:
97:
23:
164:
information retrieval system must incorporate methods of both sorting past data and managing new data.
126:
Any person employed by an employer, including trainees and apprentices but excluding domestic servants;
823:
Ashley, K.D.; Bruninghaus, S. (2009). "Automatically classifying case texts and predicting outcomes".
120:
705:
612:
604:
840:
811:
790:
Proceedings of the fourth international conference on
Artificial intelligence and law - ICAIL '93
776:
747:
718:
679:
634:
101:
231:(NLP) techniques that are adapted to the legal domain, and also require the creation of a legal
801:
624:
108:
countries, where each decided case can subtly change the meaning of a certain word or phrase.
35:
832:
793:
768:
739:
710:
669:
661:
616:
54:
cases. In some jurisdictions this may be especially problematic, as legal professionals are
609:
Proceedings of the seventh international conference on
Information and knowledge management
77:(words that have different meanings when used in a legal context), and constant change.
177:
149:
81:
66:
42:
123:
who habitually uses display screen equipment as a significant part of his normal work.
868:
844:
815:
751:
722:
683:
638:
55:
51:
780:
580:
184:
153:
62:
46:
27:
312:
836:
772:
743:
714:
691:
Peters, W.; et al. (2007). "The structuring of legal knowledge in LOIS".
207:
105:
80:
Techniques used to achieve these goals generally fall into three categories:
251:
236:
74:
797:
620:
674:
232:
198:
31:
311:
American Bar
Association, Model Rules of Professional Conduct Rule 1.1,
203:
665:
70:
58:
obligated to be reasonably informed as to relevant legal documents.
361:
359:
441:
69:). This is a difficult task, as the legal field is prone to
451:
449:
409:
407:
65:) and reducing the number of irrelevant documents (a high
426:
298:
296:
294:
585:
Frontiers in
Artificial Intelligence and Applications
581:"Concept and Context in Legal Information Retrieval"
84:
retrieval, manual classification of legal text, and
482:Schweighofer, E. and Liebwald, D. 2008, p. 108
788:Gelbart, D.; Smith, J.C. (1993). "Flexicon".
554:Ashley, K.D. and Bruninghaus, S. 2009, p. 126
527:Ashley, K.D. and Bruninghaus, S. 2009, p. 159
503:Ashley, K.D. and Bruninghaus, S. 2009, p. 125
140:A person who works at a specific occupation.
8:
313:http://www.abanet.org/cpr/mrpc/rule_1_1.html
379:
377:
375:
373:
371:
523:
521:
511:
509:
499:
497:
704:
673:
545:Maxwell, K.T., and Schafer, B. 2009, p. 9
536:Maxwell, K.T., and Schafer, B. 2009, p. 3
491:Maxwell, K.T., and Schafer, B. 2008, p. 4
455:Maxwell, K.T., and Schafer, B. 2008, p. 3
413:Maxwell, K.T., and Schafer, B. 2008, p. 2
383:Maxwell, K.T., and Schafer, B. 2008, p. 8
302:Blair, D.C., and Maron, M.E., 1985, p.293
284:
282:
280:
278:
276:
270:Maxwell, K.T., and Schafer, B. 2009, p. 1
227:These automatic systems generally employ
119:Any worker as defined in Article 3(a) of
515:Gelbart, D. and Smith, J.C. 1993, p. 142
392:Maxwell, K.T., and Schafer, B. 2007, p.1
340:
338:
263:
436:
434:
421:
419:
152:may be more relevant than those from
7:
16:Techniques for searching legal texts
579:Maxwell, K.T.; Schafer, B. (2008).
464:Saravanan, M. et al. 2009, p. 116
353:Saravanan, M. et al. 2009, p. 101
14:
603:Jackson, P.; et al. (1998).
473:Saravanan, M. et al. 2009, p. 103
401:Saravanan M., et al. 2009, p. 116
136:It also has the common meaning:
26:applied to legal text, including
860:Computer-assisted legal research
825:Artificial Intelligence and Law
761:Artificial Intelligence and Law
732:Artificial Intelligence and Law
693:Artificial Intelligence and Law
365:Peters, W. et al. 2007, p. 131
344:Peters, W. et al. 2007, p. 120
332:Peters, W. et al. 2007, p. 130
323:Peters, W. et al. 2007, p. 118
1:
875:Information retrieval genres
880:Natural language processing
229:Natural Language Processing
222:Natural language processing
86:natural language processing
20:Legal information retrieval
906:
611:. Cikm '98. ACM. pp.
837:10.1007/s10506-009-9077-9
792:. ACM. pp. 142–151.
773:10.1007/s10506-007-9029-1
744:10.1007/s10506-009-9075-y
715:10.1007/s10506-007-9034-4
654:Communications of the ACM
442:http://www.lexisnexis.com
206:'s “Natural Language” or
112:Legal information systems
96:Application of standard
138:
427:http://www.westlaw.com
246:Citation-Based ranking
798:10.1145/158976.158994
621:10.1145/288627.288642
288:Jackson et al., p. 60
192:Manual classification
98:information retrieval
24:information retrieval
890:Online law databases
121:Directive 89/391/EEC
425:Westlaw Research,
22:is the science of
666:10.1145/3166.3197
36:legal informatics
897:
848:
819:
784:
755:
726:
708:
687:
677:
648:
646:
645:
599:
597:
596:
565:
561:
555:
552:
546:
543:
537:
534:
528:
525:
516:
513:
504:
501:
492:
489:
483:
480:
474:
471:
465:
462:
456:
453:
444:
440:Lexis Research,
438:
429:
423:
414:
411:
402:
399:
393:
390:
384:
381:
366:
363:
354:
351:
345:
342:
333:
330:
324:
321:
315:
309:
303:
300:
289:
286:
271:
268:
178:Boolean searches
173:Boolean searches
905:
904:
900:
899:
898:
896:
895:
894:
865:
864:
856:
851:
822:
808:
787:
758:
729:
706:10.1.1.104.7469
690:
651:
643:
641:
631:
602:
594:
592:
578:
574:
569:
568:
562:
558:
553:
549:
544:
540:
535:
531:
526:
519:
514:
507:
502:
495:
490:
486:
481:
477:
472:
468:
463:
459:
454:
447:
439:
432:
424:
417:
412:
405:
400:
396:
391:
387:
382:
369:
364:
357:
352:
348:
343:
336:
331:
327:
322:
318:
310:
306:
301:
292:
287:
274:
269:
265:
260:
248:
224:
194:
175:
170:
150:superior courts
94:
88:of legal text.
17:
12:
11:
5:
903:
901:
893:
892:
887:
885:Legal research
882:
877:
867:
866:
863:
862:
855:
852:
850:
849:
831:(2): 125–165.
820:
807:978-0897916066
806:
785:
767:(2): 103–115.
756:
738:(2): 101–124.
727:
699:(2): 117–135.
688:
660:(3): 289–299.
649:
630:978-1581130614
629:
600:
575:
573:
570:
567:
566:
556:
547:
538:
529:
517:
505:
493:
484:
475:
466:
457:
445:
430:
415:
403:
394:
385:
367:
355:
346:
334:
325:
316:
304:
290:
272:
262:
261:
259:
256:
247:
244:
223:
220:
193:
190:
174:
171:
169:
166:
142:
141:
134:
133:
130:
127:
124:
93:
90:
67:precision rate
43:boolean search
15:
13:
10:
9:
6:
4:
3:
2:
902:
891:
888:
886:
883:
881:
878:
876:
873:
872:
870:
861:
858:
857:
853:
846:
842:
838:
834:
830:
826:
821:
817:
813:
809:
803:
799:
795:
791:
786:
782:
778:
774:
770:
766:
762:
757:
753:
749:
745:
741:
737:
733:
728:
724:
720:
716:
712:
707:
702:
698:
694:
689:
685:
681:
676:
675:2027.42/35415
671:
667:
663:
659:
655:
650:
640:
636:
632:
626:
622:
618:
614:
610:
606:
601:
590:
586:
582:
577:
576:
571:
560:
557:
551:
548:
542:
539:
533:
530:
524:
522:
518:
512:
510:
506:
500:
498:
494:
488:
485:
479:
476:
470:
467:
461:
458:
452:
450:
446:
443:
437:
435:
431:
428:
422:
420:
416:
410:
408:
404:
398:
395:
389:
386:
380:
378:
376:
374:
372:
368:
362:
360:
356:
350:
347:
341:
339:
335:
329:
326:
320:
317:
314:
308:
305:
299:
297:
295:
291:
285:
283:
281:
279:
277:
273:
267:
264:
257:
255:
253:
245:
243:
240:
238:
234:
230:
221:
219:
215:
211:
209:
205:
200:
191:
189:
186:
181:
179:
172:
167:
165:
161:
157:
155:
151:
145:
139:
137:
131:
128:
125:
122:
118:
117:
116:
113:
109:
107:
103:
99:
91:
89:
87:
83:
78:
76:
72:
68:
64:
59:
57:
53:
48:
44:
39:
37:
33:
29:
25:
21:
828:
824:
789:
764:
760:
735:
731:
696:
692:
657:
653:
642:. Retrieved
608:
593:. Retrieved
588:
584:
559:
550:
541:
532:
487:
478:
469:
460:
397:
388:
349:
328:
319:
307:
266:
249:
241:
225:
216:
212:
195:
182:
176:
162:
158:
154:lower courts
146:
143:
135:
111:
110:
95:
79:
60:
52:precedential
40:
19:
18:
185:recall rate
63:recall rate
47:recall rate
28:legislation
869:Categories
644:2009-11-07
595:2009-11-07
572:References
208:LexisNexis
168:Techniques
106:common law
701:CiteSeerX
252:Page Rank
237:f-measure
75:polysemes
56:ethically
854:See also
845:31791294
816:18952317
233:ontology
199:ontology
102:taxonomy
92:Problems
32:case law
752:8853001
723:2355864
684:5144091
639:1268465
591:: 63–72
204:Westlaw
82:boolean
843:
814:
804:
779:
750:
721:
703:
682:
637:
627:
71:jargon
841:S2CID
812:S2CID
781:80124
777:S2CID
748:S2CID
719:S2CID
680:S2CID
635:S2CID
613:60–67
258:Notes
802:ISBN
625:ISBN
564:ACM.
833:doi
794:doi
769:doi
740:doi
711:doi
670:hdl
662:doi
617:doi
589:189
871::
839:.
829:17
827:.
810:.
800:.
775:.
765:15
763:.
746:.
736:17
734:.
717:.
709:.
697:15
695:.
678:.
668:.
658:28
656:.
633:.
623:.
615:.
607:.
587:.
583:.
520:^
508:^
496:^
448:^
433:^
418:^
406:^
370:^
358:^
337:^
293:^
275:^
73:,
38:.
30:,
847:.
835::
818:.
796::
783:.
771::
754:.
742::
725:.
713::
686:.
672::
664::
647:.
619::
598:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.