An end-to-end joint model for evidence information extraction from court record document. Issue 6 (November 2020)

• Record Type: Journal Article
• Authors: Ji, Donghong; Tao, Peng; Fei, Hao; Ren, Yafeng
• Is Part Of: Information processing & management. Volume 57:Issue 6(2020:Nov.)
• Publication Date: 2020-11
• Subjects: Natural language processing -- Information extraction -- Court record document -- Neural networks -- Joint model; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2020.102305
• Languages: English
• ISSNs: 0306-4573

Abstract

Highlights: We explore a new task of information extraction, which aims to extract evidence information from count record documents in the legal domain. We formalize evidence information extraction task as an integration of paragraph classification and sequence labeling problem, and propose an end-to-end joint model for the task. Our model achieves the current best performances, outperforming previous methods and neural baseline systems by a large margin. The proposed model can be applied for better analyzing and understanding legal texts, avoiding a lot of manual work for experts and professionals in the legal domain. Abstract: Information extraction is one of the important tasks in the field of Natural Language Processing (NLP). Most of the existing methods focus on general texts and little attention is paid to information extraction in specialized domains such as legal texts. This paper explores the task of information extraction in the legal field, which aims to extract evidence information from court record documents (CRDs). In the general domain, entities and relations are mostly words and phrases, indicating that they do not span multiple sentences. In contrast, evidence information in CRDs may span multiple sentences, while existing models cannot handle this situation. To address this issue, we first add a classification task in addition to the extraction task. We then formulate the two tasks as a multi-task learning problem and present a novel end-to-end model to jointly address the two tasks. The joint model adopts a shared encoder followed by separate decoders for the two tasks. The experimental results on the dataset show the effectiveness of the proposed model, which can obtain 72.36% F1 score, outperforming previous methods and strong baselines by a large margin.