Survey of Research on Intelligent System for Legal Domain

doi:10.3778/j.issn.1002-8331.2208-0383

Abstract

Abstract: With the improvement of people’s awareness of law and the continuous advancement of judicial digital reform, judicial organs and some corresponding platforms have accumulated a large amount of legal data. On this basis, it is critical to research and develop an intelligent system for legal domain using artificial intelligence algorithm, which cannot only assist legal practitioners in processing large amounts of data, but also provide convenient and cheap legal consultation services to the general public. This paper summarizes the topic of intelligent systems for legal domain, and selects four typical tasks for the research of legal intelligent system according to different application scenarios, which are judicial examination, civil legal question answering, judicial machine reading comprehension and legal judgment prediction. The paper introduces the definition, relevant datasets and evaluation indicators of each type of task in detail. Then, it analyzes the key points and difficulties involved in each type of task, and summarizes reasonable and effective solutions proposed by different research teams for these problems. Based on the comparison and analysis of the latest research progress, it further explores and reveals the main factors restricting the development of legal intelligence system. Finally, it prospects the future development trend of legal intelligent system.

Key words: artificial intelligence, legal question answering, judicial examination, machine reading comprehension, legal judgment prediction

摘要： 随着人们法治意识的提高以及司法数字化改革的不断推进，司法机关和一些相应的平台都已经积累了大量的法律数据。在此基础上，借助人工智能算法研究和开发面向司法领域的智能系统具有重要的现实意义，它一方面可以协助法律从业人员分析处理海量数据，另一方面还能为普通民众提供便捷廉价的法律咨询服务等。以面向法律领域的智能系统为主题进行综述，根据不同应用场景选取了面向法律领域的智能系统研究的四个典型任务，分别是司法考试、民用法律问答、司法机器阅读理解、法律判决预测。详细介绍了每类任务的定义、相关数据集以及评价指标；对每类任务涉及到的重点和难点问题进行逐一剖析，并针对这些问题归纳出不同研究团队提出的合理有效的解决方案。在对最新的研究进展进行对比与分析的基础上，进一步探讨和揭示制约法律智能系统发展的主要因素；最后，对面向法律领域的智能系统研究的未来发展态势进行了展望。

关键词: 人工智能, 法律问答, 司法考试, 机器阅读理解, 判决预测

LI Jinchen, LI Yanling, GE Fengpei, LIN Min. Survey of Research on Intelligent System for Legal Domain[J]. Computer Engineering and Applications, 2023, 59(7): 31-50.

李瑾晨, 李艳玲, 葛凤培, 林民. 面向法律领域的智能系统研究综述[J]. 计算机工程与应用, 2023, 59(7): 31-50.

References

[1] ZHONG H，XIAO C，TU C，et al.JEC-QA：a legal-domain question answering dataset[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：9701-9708.
[2] DUAN X，WANG B，WANG Z，et al.CJRC：a reliable human-annotated benchmark dataset for Chinese judicial reading comprehension[C]//Proceedings of the Chinese Computational Linguistics：the 18th China National Conference，2019：439-451.
[3] XIAO C，ZHONG H，GUO Z，et al.Cail2018：a large-scale legal dataset for judgment prediction[J].arXiv：1807. 02478，2018.
[4] HU Z，LI X，TU C，et al.Few-shot charge prediction with discriminative legal attributes[C]//Proceedings of the 27th International Conference on Computational Linguistics.Association for Computational Linguistics，2018：487-498.
[5] KIM M Y，XU Y，GOEBEL R，et al.Answering yes/no questions in legal bar exams[C]//Proceedings of the New Frontiers in Artificial Intelligence：JSAI-isAI 2013 Workshops，2014：199-213.
[6] KIM M Y，XU Y，GOEBEL R.Legal question answering using ranking svm and syntactic/semantic similarity[C]//Proceedings of the New Frontiers in Artificial Intelligence：JSAI-isAI 2014 Workshops，2015：244-258.
[7] TANIGUCHI R，KANO Y.Legal yes/no question answering system using case-role analysis[C]//Proceedings of the New Frontiers in Artificial Intelligence：JSAI-isAI 2016 Workshops，2017：284-298.
[8] TANIGUCHI R，HOSHINO R，KANO Y.Legal question answering system using framenet[C]//Proceedings of the New Frontiers in Artificial Intelligence：JSAI-isAI 2018 Workshops，2019：193-206.
[9] CARVALHO D S，NGUYEN M T，TRAN C X，et al.Lexical-morphological modeling for legal text analysis[J].arXiv：1609.00799，2016.
[10] KIM M Y，XU Y，GOEBEL R.Applying a convolutional neural network to legal question answering[C]//Proceedings of the New Frontiers in Artificial Intelligence：JSAI-isAI 2015 Workshops，2017：282-294.
[11] KIM M Y，LU Y，GOEBEL R.Textual entailment in legal bar exam question answering using deep siamese networks[C]//Proceedings of the New Frontiers in Artificial Intelligence：JSAI-isAI 2017 Workshops，2018：35-48.
[12] MORIMOTO A，KUBO D，SATO M，et al.Legal question answering system using neural attention[C]//Proceedings of the COLIEE@ICAIL2017，2017：79-89.
[13] GAIN B，BANDYOPADHYAY D，SAIKH T，et al.Iitp@ coliee 2019：legal information retrieval using BM25 and BERT[J].arXiv：2104.08653，2021.
[14] DEVLIN J，CHANG M W，LEE K，et al.BERT：pre-training of deep bidirectional transformers for language understanding[J].arXiv：1810.04805，2018.
[15] YOSHIOKA M，AOKI Y，SUZUKI Y.BERT-based ensemble methods with data augmentation for legal textual entailment in COLIEE statute law task[C]//Proceedings of the 18th International Conference on Artificial Intelligence and Law，2021：278-284.
[16] BENDER E M，GEBRU T，MCMILLAN-MAJOR A，et al.On the dangers of stochastic parrots：can language models be too big?[C]//Proceedings of the 2021 ACM Conference on Fairness，Accountability，and Transparency，2021：610-623.
[17] NGUYEN H-T，VUONG H Y T，NGUYEN P M，et al.JNLP team：deep learning for legal processing in coliee 2020[J].arXiv：2011.08071，2020.
[18] WU J，LUO X.Alignment-based graph network for judicial examination task[C]//Proceedings of the 14th International Conference on Knowledge Science，Engineering and Management，2021：386-400.
[19] ZHONG H，XIAO C，TU C，et al.How does NLP benefit legal system：a summary of legal artificial intelligence[J].arXiv：2004.12158，2020.
[20] 周倚文.面向法律领域的问答系统研究[D].长沙：湖南大学，2018.
ZHOU Y W.The research of question answering system for law domain[D].Changsha：Hunan University，2018.
[21] JOULIN A，GRAVE E，BOJANOWSKI P，et al.Fasttext.zip：compressing text classification models[J].arXiv：1612. 03651，2016.
[22] 涂海，彭敦陆，陈章，等.S2SA-BiLSTM：面向法律纠纷智能问答系统的深度学习模型[J].小型微型计算机系统，2019，40（5）：1034-1039.
TU H，PENG D L，CHEN Z，et al.S2SA-BiLSTM：a deep learning model towards intelligent Q&A system for legal disputes[J].Journal of Chinese Computer Systems，2019，40（5）：1034-1039.
[23] GRAVES A，SCHMIDHUBER J.Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J].Neural Networks，2005，18（5/6）：602-610.
[24] 林智敏.基于深度学习的法律判决文书问答系统研究[D].重庆：重庆邮电大学，2021.
LING Z M.Research on question answering system of legal judgment documents based on deep learning[D].Chongqing：Chongqing University of Posts and Telecommunications，2021.
[25] VOLD A，CONRAD J G.Using transformers to improve answer retrieval for legal questions[C]//Proceedings of the 18th International Conference on Artificial Intelligence and Law，2021：245-249.
[26] LIU Y，OTT M，GOYAL N，et al.Roberta：a robustly optimized bert pretraining approach[J].arXiv：1907. 11692，2019.
[27] KHAZAELI S，PUNURU J，MORRIS C，et al.A free format legal question answering system[C]//Proceedings of the Natural Legal Language Processing Workshop，2021：107-113.
[28] ROBERTSON S，ZARAGOZA H.The probabilistic relevance framework：BM25 and beyond[J].Foundations and Trends? in Information Retrieval，2009，3（4）：333-389.
[29] 刘依红，杨波，孙宇宁，等.基于BiLSTM的婚姻法自然语言问答[J].计算机工程与设计，2019，40（4）：1190-1195.
LIU Y H，YANG B，SUN Y N，et al.Q&A of natural language in marriage law based on BiLSTM[J].Computer Engineering and Design，2019，40（4）：1190-1195.
[30] HUANG W，JIANG J，QU Q，et al.AILA：a question answering system in the legal domain[C]//Proceedings of the IJCAI Conference，2020：5258-5260.
[31] 杜何哲.融合知识图谱的林业法律法规问答系统研建[D].北京：北京林业大学，2020.
DU H Z.Research and construction on a knowledge graph integrated question answering system of forestry laws and regulations[D].Beijing：Beijing Forestry University，2020.
[32] 汪汇.基于法律知识图谱的自动问答系统[D].南京：南京大学，2021.
WANG H.Automatic question answering system based on legal knowledge graph[D].Nanjing：Nanjing University，2021.
[33] LAN Z，CHEN M，GOODMAN S，et al.AlBERT：a lite bert for self-supervised learning of language representations[J].arXiv：1909.11942，2019.
[34] LAFFERTY J，MCCALLUM A，PEREIRA F.Conditional random fields：probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the ICML 2001 Conference，2001.
[35] 陈金菊，王义真，欧石燕.基于道路法规知识图谱的多轮自动问答研究[J].现代情报，2020，40（8）：98-110.
CHEN J J，WANG Y Z，OU S Y.Research on multi-round automatic question answering based on knowledge graph of road regulations[J].Journal of Modern Information，2020，40（8）：98-110.
[36] 黄辉.面向盗窃案件的智能问答方法研究及其应用[D].贵阳：贵州大学，2021.
HUANG H.Research and application of intelligent question answering method for theft cases[D].Guiyang：Guizhou University，2021.
[37] JIAO X，YIN Y，SHANG L，et al.TinyBERT：distilling bert for natural language understanding[J].arXiv：1909. 10351，2019.
[38] CUI Y，CHE W，LIU T，et al.Pre-training with whole word masking for Chinese BERT[J].IEEE/ACM Transactions on Audio，Speech，and Language Processing，2021，29：3504-3514.
[39] SEO M，KEMBHAVI A，FARHADI A，et al.Bidirectional attention flow for machine comprehension[J].arXiv：1611.01603，2016.
[40] 曾俊.抽取式中文机器阅读理解研究[D].武汉：华中师范大学，2020.
ZENG J.Research of extractive Chinese machine reading comprehension[D].Wuhan：Central China Normal University，2020.
[41] 谭红叶，屈保兴.面向多类型问题的阅读理解方法研究[J].中文信息学报，2020，34（6）：81-88.
TAN H Y，QU B X.An approach to multi-type question machine reading comprehension[J].Journal of Chinese Information Processing，2020，34（6）：81-88.
[42] 王寰，孙雷，吴斌，等.基于阅读理解智能问答的RPR融合模型研究[J].计算机应用研究，2021，39（3）：1-8.
WANG H，SUN L，WU B，et al.Research on RPR fusion model based on reading comprehension intelligent question answering[J].Application Research of Computers，2021，39（3）：1-8.
[43] 张虎，王宇杰，谭红叶，等.基于MHSA和句法关系增强的机器阅读理解方法研究[J].自动化学报，2022，48（11）：2718-2728.
ZHANG H，WANG Y J，TAN H Y，et al.Research on machine reading comprehension method based on MHSA and syntactic relations enhancement[J].Acta Automatica Sinica，2022，48（11）：2718-2728.
[44] 李芳芳，任星凯，毛星亮，等.基于多任务联合训练的法律文本机器阅读理解模型[J].中文信息学报，2021，35（7）：109-117.
LI F F，REN X K，MAO X L，et al.A reading comprehension model for judical texts based on multi task joint training[J].Journal of Chinese Information Processing，2021，35（7）：109-117.
[45] RAJPURKAR P，ZHANG J，LOPYREV K，et al.Squad：100，000+ questions for machine comprehension of text[J].arXiv：1606.05250，2016.
[46] REDDY S，CHEN D，MANNING C D.CoQA：a conversational question answering challenge[J].Transactions of the Association for Computational Linguistics，2019，7：249-266.
[47] HE W，LIU K，LIU J，et al.Dureader：a Chinese machine reading comprehension dataset from real-world applications[J].arXiv：1711.05073，2017.
[48] YANG Z，QI P，ZHANG S，et al.HotpotQA：a dataset for diverse，explainable multi-hop question answering[J].arXiv：1809.09600，2018.
[49] 闫凯峰.中文机器阅读理解系统的研究与实现[D].大庆：东北石油大学，2021.
YAN K F.Research and implementation of Chinese machine reading comprehension system[D].Daqing：Northeast Petroleum University，2021.
[50] 秦永彬，黄辉，王凯.司法机器阅读理解的优化策略研究[J].华中科技大学学报（自然科学版），2022，50（2）：142-148.
QIN Y B，HUANG H，WANG K，et al.Research on optimizing strategies of judicial machine reading comprehension[J].Journal of Huazhong University of Science and Technology（Natural Science Edition），2022，50（2）：142-148.
[51] DONG L，YANG N，WANG W，et al.Unified language model pre-training for natural language understanding and generation[C]//Advances in Neural Information Processing Systems，2019.
[52] ZAHEER M，GURUGANESH G，DUBEY A，et al.Big bird：transformers for longer sequences[C]//Advances in Neural Information Processing Systems，2020：17283-17297.
[53] BELTAGY I，PETERS M E，COHAN A.Longformer：the long-document transformer[J].arXiv：2004.05150，2020.
[54] DAI Z，YANG Z，YANG Y，et al.Transformer-XL：attentive language models beyond a fixed-length context[J].arXiv：1901.02860，2019.
[55] LIMSOPATHAM N.Effectively leveraging BERT for legal document classification[C]//Proceedings of the Natural Legal Language Processing Workshop，2021：210-216.
[56] WANG S，YU M，CHANG S，et al.A co-matching model for multi-choice reading comprehension[J].arXiv：1806. 04068，2018.
[57] ZHU H，WEI F，QIN B，et al.Hierarchical attention flow for multiple-choice reading comprehension[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2018.
[58] ZHONG H，GUO Z，TU C，et al.Legal judgment prediction via topological learning[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing，2018：3540-3549.
[59] YANG W，JIA W，ZHOU X，et al.Legal judgment prediction via multi-perspective bi-feedback network[J].arXiv：1905.03969，2019.
[60] DONG Q，NIU S.Legal judgment prediction via relational learning[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval，2021：983-992.
[61] LUO B，FENG Y，XU J，et al.Learning to predict charges for criminal cases with legal basis[J].arXiv：1707.09168，2017.
[62] CHEN S，WANG P，FANG W，et al.Learning to predict charges for judgment with legal graph[C]//Proceedings of the Artificial Neural Networks and Machine Learning-ICANN 2019 Conference，2019：240-252.
[63] XU N，WANG P，CHEN L，et al.Distinguish confusing law articles for legal judgment prediction[J].arXiv：2004.02557，2020.
[64] YUE L，LIU Q，JIN B，et al.Neurjudge：a circumstance-aware neural framework for legal judgment prediction[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval，2021：973-982.
[65] YUAN L，WANG J，FAN S，et al.Automatic legal judgment prediction via large amounts of criminal cases[C]//Proceedings of the 2019 IEEE 5th International Conference on Computer and Communications （ICCC），2019：2087-2091.
[66] DOSHI-VELEZ F，KIM B.Towards a rigorous science of interpretable machine learning[J].arXiv：1702.08608，2017.
[67] XU Z P，LI X，LI Y L，et al.Multi-task legal judgement prediction combining a subtask of the seriousness of charges[C]//Proceedings of the Chinese Computational Linguistics：the 19th China National Conference，2020：415-429.
[68] 张博文.自动刑期预测及其可解释性研究[D].太原：山西大学，2020.
ZHANG B W.Research on automatic penalty prediction and interpretability[D].Taiyuan：Shanxi University，2020.
[69] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[70] BI B，LI C，WU C，et al.PALM：pretraining an autoencoding & autoregressive language model for context-conditioned generation[J].arXiv：2004.07159，2020.
[71] SUN Y，WANG S，FENG S，et al.Ernie 3.0：large-scale knowledge enhanced pre-training for language understanding and generation[J].arXiv：2107.02137，2021.
[72] 丛颖男，王兆毓，朱金清.关于法律人工智能数据和算法问题的若干思考[J].计算机科学，2022，49（4）：74-79.
CONG Y N，WANG Z Y，ZHU J Q.Insights into dataset and algorithm related problems in artificial intelligence for law[J].Computer Science，2022，49（4）：74-79.
[73] WEI J，ZOU K.EDA：easy data augmentation techniques for boosting performance on text classification tasks[J].arXiv：1901.11196，2019.
[74] SUN Y，WANG S，LI Y，et al.Ernie：enhanced representation through knowledge integration[J].arXiv：1904. 09223，2019.
[75] ZHONG H，ZHANG Z，LIU Z，et al.Open Chinese language pre-trained model zoo[R].2019.
[76] XIAO C，HU X，LIU Z，et al.Lawformer：a pre-trained language model for Chinese legal long documents[J].AI Open，2021，2：79-84.
[77] CLARK K，LUONG M T，LE Q V，et al.Electra：pre-training text encoders as discriminators rather than generators[J].arXiv：2003.10555，2020.
[78] CHALKIDIS I，FERGADIOTIS M，MALAKASIOTIS P，et al.LEGAL-BERT：the muppets straight out of law school[J].arXiv：2010.02559，2020.
[79] DOUKA S，ABDINE H，VAZIRGIANNIS M，et al.JuriBERT：a masked-language model adaptation for french legal text[J].arXiv：2110.01485，2021.
[80] MASALA M，IACOB R C A，UBAN A S，et al.JurBERT：a romanian bert model for legal judgement prediction[C]//Proceedings of the Natural Legal Language Processing Workshop，2021：86-94.
[81] WEI J，REN X，LI X，et al.NEZHA：neural contextualized representation for Chinese language understanding[J].arXiv：1909.00204，2019.
[82] SU J，LU Y，PAN S，et al.RoFormer：enhanced transformer with rotary position embedding[J].arXiv：2104. 09864，2021.