证据作为认定案件事实的基础,在司法实践中起着重要的辅助判决作用。正常来说,一篇文书中相关的证据会被分为几个不相交子集,每个子集所证明的内容被视为司法分论点,这些分论点支撑了案件事实的不同方面,从而有利于法官的最终判决。然而,以前的工作主要集中在法庭观点生成,或其他法律助理系统(如法律判决预测和司法问答),忽视了法律文书中的证据推理。为了还原法律案件中完整的证据证明、推理过程,该文提出了基于自动证据推理的分论点生成任务,即基于证据子集生成司法分论点。该文为此任务提出了一个双重注意力网络模型,从事实描述中挖掘与证据相关的语义以及法律知识,并结合解码器自动生成分论点。为了进行评估,该文构建了一个司法分论点数据集,并进行了相关实验来证明所提出模型的有效性。
Abstract
Evidence as the basis of determining the facts of legal cases plays an important role of factfinding and judgment in judicial practice. Usually, evidence collection is divided into several subsets to support different aspects of the facts in favor of final conviction, where the proven contents are considered as sub-claims to support the main judgment. However, previous work mainly focuses on courtview generation, or other legal assistant system(e.g., legal judgment prediction and question answering), neglecting the evidential reasoning in the legal documents. To restore the complete process of evidence proof in legal cases, in this paper, we propose the task of sub-claim generation towards automated evidential reasoning, i.e., generating a sub-claim based on a subset of evidence. We propose a dual-attention network model to explore evidence-related semantics and legal knowledge from fact description, combined with a decoder to generate sub-claim automatically. We also construct a real-world dataset and conduct extensive experiments to demonstrate the effectiveness of the proposed model.
关键词
司法分论点 /
证据推理 /
文本生成
{{custom_keyword}} /
Key words
legal sub-claim /
evidential reasoning /
text generation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] LOWRANCE J D, GARVEY T D. Evidential reasoning: A developing concept[C]//Proceedings of the International Conference on Cyberneticy and Society, 1982: 6-9.
[2] LAGNADO D A, FENTON N, NEIL M. Legal idioms: A framework for evidential reasoning[J]. Argument & Computation, 2013, 4(1): 46-63.
[3] TENG Y, CHAO W. Argumentation driven evidence association in criminal cases[G]//Proceedings of the Association for Computational Linguistics: EMNLP, 2021: 2997-3001.
[4] GALGANI F, COMPTON P, HOFFMANN A. Combining different summarization techniques for legal text[C]//Proceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data, 2012: 115-123.
[5] POLSLEY S, JHUNJHUNWALA P, HUANG R. Casesummarizer: A system for automated summarization of legal texts[C]//Proceedings of COLING, the 26th International Conference on Computational Linguistics: System Demonstrations, 2016: 258-262.
[6] YE H, JIANG X, LUO Z, et al. Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018: 1854-1864.
[7] LI Q, ZHANG Q. Court opinion generation from case fact description with legal basis[C]//Proceedings of the AAAI Conference on Artificial Intelligence: 2021(35): 14840-14848.
[8] SCHILDER F, MOLINASALGADO H. Evaluating a summarizer for legal text with a large text collection[C]//Proceedings of the 3rd Midwestern Computational Linguistics Colloquium, 2006.
[9] GALGANI F, COMPTON P, HOFFMANN A. Citation based summarisation of legal texts[C]//Proceedings of the Pacific Rim International Conference on Artificial Intelligence. Springer, 2012: 40-52.
[10] FU J, LIU J, TIAN H, et al. Dual attention network for scene segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 3146-3154.
[11] VINYALS O, FORTUNATO M, JAITLY N. Pointer networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems, 2015: 2692-2700.
[12] JI D, TAO P, FEI H, et al. An end-to-end joint model for evidence information extraction from court record document[J]. Information Processing & Management, 2020, 57(6): 102305.
[13] ALI B, MORE R, PAWAR S, et al. Prior case retrieval using evidence extraction from court judgements[C]//Processings of ASAIL/LegalAIIA@ICAIC,2021: 1-11.
[14] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minnesota: Association for Computational Linguistics, 2019: 4171-4186.
[15] CHEN Q, ZHU X, LING Z H, et al. Enhanced LSTM for natural language inference[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 1657-1668.
[16] WU Y, KUANG K, ZHANG Y, et al. Debiased court's view generation with causality[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 763-780.
[17] YUE L, LIU Q, WU H, et al. Circumstances enhanced criminal court view generation[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021: 1855-1859.
[18] LIU Y, LAPATA M. Text summarization with pretrained encoders[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 3730-3740.
[19] SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014: 3104-3112.
[20] DU X, SHAO J, CARDIE C. Learning to ask: Neural question generation for reading comprehension[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics,2017: 1342-1352.
[21] LEWIS M, LIU Y, GOYAL N, et al. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics,2020: 7871-7880.
[22] PAPINENI K, ROUKOS S, WARD T, et al. BLEU: A method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. USA, 2002: 311-318.
[23] ZHANG T, KISHORE V, WU F, et al. Bertscore: Evaluating text generation with bert[C]//Proceedings of ICLR, 2020: 1-43.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61976221)
{{custom_fund}}
PDF(4579 KB)
