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

School of Computer Science and Engineering

Beihang University
Academy of Military Medical Science China

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

113 Scopus citations

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.

Original language	English
Title of host publication	Long Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	1854-1864
Number of pages	11
ISBN (Electronic)	9781948087278
State	Published - 2018
Event	2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, United States Duration: 1 Jun 2018 → 6 Jun 2018

Publication series

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

Conference

Conference	2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
Country/Territory	United States
City	New Orleans
Period	1/06/18 → 6/06/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 16 Peace, Justice and Strong Institutions

Cite this

Ye, H., Jiang, X., Luo, Z., & Chao, W. (2018). Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. In Long Papers (pp. 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; Vol. 1). Association for Computational Linguistics (ACL).

Ye, Hai ; Jiang, Xin ; Luo, Zhunchen et al. / Interpretable charge predictions for criminal cases : Learning to generate court views from fact descriptions. Long Papers. Association for Computational Linguistics (ACL), 2018. pp. 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. in 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, vol. 1, Association for Computational Linguistics (ACL), pp. 1854-1864, 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018, New Orleans, United States, 1/06/18.

Interpretable charge predictions for criminal cases: Learning to generate court views from fact descriptions. / Ye, Hai; Jiang, Xin; Luo, Zhunchen et al.
Long Papers. Association for Computational Linguistics (ACL), 2018. p. 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; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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. In Long Papers. Association for Computational Linguistics (ACL). 2018. p. 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

Abstract

Publication series

Conference

UN SDGs

Other files and links

Fingerprint

Cite this