Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions

Hai Ye; Xin Jiang; Zhunchen Luo; Wenhan Chao

Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions

Hai Ye
, Xin Jiang
, Zhunchen Luo
, Wenhan Chao

计算机学院

Beihang University
Academy of Military Medical Science China

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

113 引用（Scopus）

摘要

In this paper, we propose to study the problem of COURT VIEW GENeration from the fact description in a criminal case. The task aims to improve the interpretability of charge prediction systems and help automatic legal document generation. We formulate this task as a text-To-Text natural language generation (NLG) problem. Sequenceto-sequence model has achieved cutting-edge performances in many NLG tasks. However, due to the non-distinctions of fact descriptions, it is hard for Seq2Seq model to generate charge-discriminative court views. In this work, we explore charge labels to tackle this issue. We propose a label-conditioned Seq2Seq model with attention for this problem, to decode court views conditioned on encoded charge labels. Experimental results show the effectiveness of our method.

源语言	英语
主期刊名	Long Papers
出版商	Association for Computational Linguistics (ACL)
页	1854-1864
页数	11
ISBN（电子版）	9781948087278
出版状态	已出版 - 2018
活动	2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, 美国期限: 1 6月 2018 → 6 6月 2018

出版系列

姓名	NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
卷	1

会议

会议	2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
国家/地区	美国
市	New Orleans
时期	1/06/18 → 6/06/18

联合国可持续发展目标

此成果有助于实现下列可持续发展目标：

可持续发展目标 16 和平、正义和强大机构

其它文件与链接

链接到 Scopus 的出版物

引用此

Ye, H., Jiang, X., Luo, Z., & Chao, W. (2018). Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. 在 Long Papers (页码 1854-1864). (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; 卷 1). Association for Computational Linguistics (ACL).

Ye, Hai ; Jiang, Xin ; Luo, Zhunchen 等. / Interpretable charge predictions for criminal cases : Learning to generate court views from fact descriptions. Long Papers. Association for Computational Linguistics (ACL), 2018. 页码 1854-1864 (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference).

@inproceedings{ae37d901100a434a8d11f417c2056ee0,

title = "Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions",

abstract = "In this paper, we propose to study the problem of COURT VIEW GENeration from the fact description in a criminal case. The task aims to improve the interpretability of charge prediction systems and help automatic legal document generation. We formulate this task as a text-To-Text natural language generation (NLG) problem. Sequenceto-sequence model has achieved cutting-edge performances in many NLG tasks. However, due to the non-distinctions of fact descriptions, it is hard for Seq2Seq model to generate charge-discriminative court views. In this work, we explore charge labels to tackle this issue. We propose a label-conditioned Seq2Seq model with attention for this problem, to decode court views conditioned on encoded charge labels. Experimental results show the effectiveness of our method.",

author = "Hai Ye and Xin Jiang and Zhunchen Luo and Wenhan Chao",

note = "Publisher Copyright: {\textcopyright} 2018 The Association for Computational Linguistics.; 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",

year = "2018",

language = "英语",

series = "NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1854--1864",

booktitle = "Long Papers",

address = "澳大利亚",

}

Ye, H, Jiang, X, Luo, Z & Chao, W 2018, Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. 在 Long Papers. NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, 卷 1, Association for Computational Linguistics (ACL), 页码 1854-1864, 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018, New Orleans, 美国, 1/06/18.

Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. / Ye, Hai; Jiang, Xin; Luo, Zhunchen 等.
Long Papers. Association for Computational Linguistics (ACL), 2018. 页码 1854-1864 (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; 卷 1).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Interpretable charge predictions for criminal cases

T2 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018

AU - Ye, Hai

AU - Jiang, Xin

AU - Luo, Zhunchen

AU - Chao, Wenhan

PY - 2018

Y1 - 2018

N2 - In this paper, we propose to study the problem of COURT VIEW GENeration from the fact description in a criminal case. The task aims to improve the interpretability of charge prediction systems and help automatic legal document generation. We formulate this task as a text-To-Text natural language generation (NLG) problem. Sequenceto-sequence model has achieved cutting-edge performances in many NLG tasks. However, due to the non-distinctions of fact descriptions, it is hard for Seq2Seq model to generate charge-discriminative court views. In this work, we explore charge labels to tackle this issue. We propose a label-conditioned Seq2Seq model with attention for this problem, to decode court views conditioned on encoded charge labels. Experimental results show the effectiveness of our method.

AB - In this paper, we propose to study the problem of COURT VIEW GENeration from the fact description in a criminal case. The task aims to improve the interpretability of charge prediction systems and help automatic legal document generation. We formulate this task as a text-To-Text natural language generation (NLG) problem. Sequenceto-sequence model has achieved cutting-edge performances in many NLG tasks. However, due to the non-distinctions of fact descriptions, it is hard for Seq2Seq model to generate charge-discriminative court views. In this work, we explore charge labels to tackle this issue. We propose a label-conditioned Seq2Seq model with attention for this problem, to decode court views conditioned on encoded charge labels. Experimental results show the effectiveness of our method.

UR - https://www.scopus.com/pages/publications/85074944314

M3 - 会议稿件

AN - SCOPUS:85074944314

T3 - NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference

SP - 1854

EP - 1864

BT - Long Papers

PB - Association for Computational Linguistics (ACL)

Y2 - 1 June 2018 through 6 June 2018

ER -

Ye H, Jiang X, Luo Z, Chao W. Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. 在 Long Papers. Association for Computational Linguistics (ACL). 2018. 页码 1854-1864. (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference).

Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions

摘要

出版系列

会议

联合国可持续发展目标

其它文件与链接

指纹

引用此