随着人工智能与大数据技术的快速发展,基于自然语言理解的智慧司法服务研究已受到越来越多的关注。裁判文书是记载人民法院审理过程和结果的法律文本,记录了法院庭审过程中诉辩双方的完整陈述,但其缺点是未展现出具有鲜明逻辑交互关系的诉辩互动论点对,难以为法官梳理案件争议焦点提供更好的服务。目前针对互动论点对识别的研究主要面向英文论坛数据,且主要从获取论点不同层面的特征入手,所提方法的鲁棒性与泛化能力较差。该文以识别司法裁判文书中存在逻辑交互关系的诉辩论点对为目标,重点从互动论点的语义表示、互动论点对之间的交互关系和模型鲁棒性等方面进行研究,基于此,提出了结合预训练语言模型、注意力机制和对抗训练的互动论点对识别方法。实验结果表明,该文方法既提升了裁判文书诉辩互动论点对识别的精度,也提升了模型的鲁棒性。
Abstract
The research on intelligent justice service based on natural language understanding has attracted more and more attention. To better provide the judge with the focal points of the disputes in the case, this paper is focused on identifying the logical interactive argument pairs between the prosecution and the defense in the judgment documents. We investigate the semantic representation of the interactive argument, the interaction between interactive argument pairs, and so on. We present a method combining the pre-trained language model, the attention mechanism, and the adversarial training to identify interactive argument pairs. Experimental results show that the proposed method improves the accuracy in the identification of as well as the robustness of the model.
关键词
互动论点对 /
裁判文书 /
智慧司法 /
对抗训练
{{custom_keyword}} /
Key words
interactive argument pairs /
judgment documents /
intelligent justice /
adversarial training
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Tan C H, Niculae V, Danescu Niculescu Mizil C, et al. Winning arguments: Interaction dynamics and persuasion strategies in good-faith online discussions[C]//Proceedings of the 25th International World Wide Web Conference. Republic and Canton of Geneva, CHE: International World Wide Web Conferences Steering Committee, 2016: 613-624.
[2] Ji L, Wei Z Y, Li J, et al. Discrete argument representation learning for interactive argument pair identification[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021: 5467-5478.
[3] Walton D. Argumentation theory: A very short introduction[J]. Argumentation in Artificial Intelligence, 2009:1-22.
[4] Wachsmuth H. Introduction to computational argumentation[EB/OL]. https://en.cs.uni-paderborn.de/fileadmin/informatik/fg/css/computational-argumentation-s19/ca19-part01-introduction-to-computational-argumentation.pdf[2019-04-10].
[5] Besnard P, GarcíA A J, Hunter A, et al. Introduction to structured argumentation[J]. Argument and Computation, 2014, 5:1-4.
[6] Hunter A. Analysis of dialogical argumentation via finite state machines[J]. Scalable Uncertainty Management, 2013, 8078:1-14.
[7] Wachsmuth H, Potthast M, Al Khatib K, et al. Building an argument search engine for the web[C]//Proceedings of the 4th Workshop on Argument Mining. Copenhagen, Denmark: Association for Computational Linguistics, 2017: 49-59.
[8] Rinott R, Dankin L, Perez C A, et al. Show me your evidence: an automatic method for context dependent evidence detection[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Lisbon, Portugal: Association for Computational Linguistics, 2015: 440-450.
[9] Wang L, Ling W. Neural network-based abstract generation for opinions and arguments[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. San Diego, California, 2016: 47-57.
[10] Samadi M, Talukdar P, Veloso M, et al. ClaimEval: integrated and flexible framework for claim evaluation using credibility of sources[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. Phoenix, Arizona: AAAI Press, 2016: 222-228.
[11] Stab C. Argumentative writing support by means of natural language processing[D]. Darmstadt, Germany, 2017.
[12] Cabrio E, Villata S. Five years of argument mining: A data-driven analysis[C]//Proceedings of 27th International Joint Conference on Artificial Intelligence. 2018: 5427-5433.
[13] 廖祥文, 陈泽泽, 桂林, 等. 基于多任务迭代学习的论辩挖掘方法[J].计算机学报,2019(7): 1524-1538.
[14] Wachsmuth H, Stein B. A universal model for discourse-level argumentation analysis[J]. ACM Transactions on Internet Technology, 2017,17.
[15] Feng V W, Hirst G. Classifying arguments by scheme[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Portland, Oregon, USA, 2011: 987-996.
[16] Wachsmuth H, Naderi N, Hou Y F, et al. Computational argumentation quality assessment in natural language[C]//Proceedings of the 15th Conference of
the European Chapter of the Association for Computational Linguistics. Valencia, Spain, 2017: 176-187.
[17] Ji L, Wei Z Y, Hu X K, et al. Incorporating argument-level interactions for persuasion comments evaluation using co-attention model[C]//Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, New Mexico, USA, 2018: 3703-3714.
[18] Taghipour K, Ng H T. A neural approach to automated essay scoring[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Austin, Texas: Association for Computational Linguistics, 2016: 1882-1891.
[19] Bilu Y, Slonim N. Claim synthesis via predicate recycling[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany, 2016: 525-530.
[20] Sanchan N, Aker A, Bontcheva K. Automatic summarization of online debates[C]//Proceedings of the 1st Workshop on Natural Language Processing and Information Retrieval associated with {RANLP}. Varna, Bulgaria: INCOMA Inc, 2017: 19-27.
[21] Chen W F, Wachsmuth H, Al Khatib K, et al. Learning to flip the bias of news headlines[C]//Proceedings of the 11th International Conference on Natural Language Generation. Tilburg University, The Netherlands, 2018: 79-88.
[22] 杨亮, 周逢清, 张琍, 等. 基于生成对抗网络的控辩焦点识别[J].中文信息学报,2020,34(09): 89-96.
[23] Misra A, Ecker B, Walker M. Measuring the similarity of sentential arguments in dialogue[C]//Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue. Los Angeles, 2016: 276-287.
[24] Miyato T, Dai A M, Goodfellow I. Adversarial training methods for semi-supervised text classification[J]. arXiv preprint, 1605.07725, 2021.
[25] Sato M, Suzuki J, Shindo H, et al. Interpretable adversarial perturbation in input embedding space for text[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden, 2018: 4323-4330.
[26] Zhang X, Yang A, Li S J, et al. Machine reading comprehension: a literature review[J]. arXiv preprint, 2019, arXiv:1907.01686.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(62176145);国家社会科学基金(18BYY074);山西省自然科学基金(201901D111028)
{{custom_fund}}
PDF(6529 KB)
