Filters








11 Hits in 2.9 sec

Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents [article]

Chaojun Xiao, Xueyu Hu, Zhiyuan Liu, Cunchao Tu, Maosong Sun
2021 arXiv   pre-print
In this paper, we release the Longformer-based pre-trained language model, named as Lawformer, for Chinese legal long documents understanding.  ...  Recently, inspired by the success of pre-trained language models (PLMs) in the generic domain, many LegalAI researchers devote their effort to apply PLMs to legal tasks.  ...  To the best of our knowledge, Lawformer is the first pre-trained language model for legal long documents.  ... 
arXiv:2105.03887v1 fatcat:ca3dpg3ojfby5oyt6tdoyk23dm

Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents

Chaojun Xiao, Xueyu Hu, Zhiyuan Liu, Cunchao Tu, Maosong Sun
2021 AI Open  
In this paper, we release the Longformer-based pre-trained language model, named as Lawformer, for Chinese legal long documents understanding.  ...  Recently, inspired by the success of pre-trained language models (PLMs) in the generic domain, many LegalAI researchers devote their effort to applying PLMs to legal tasks.  ...  To the best of our knowledge, Lawformer is the first pre-trained language model for legal long documents.  ... 
doi:10.1016/j.aiopen.2021.06.003 fatcat:h4tbrjpolbhgzf5nnm3yfznoqy

Research on a Decision Prediction Method Based on Causal Inference and a Multi-Expert FTOPJUDGE Mechanism

Qiang Zhao, Rundong Guo, Xiaowei Feng, Weifeng Hu, Siwen Zhao, Zihan Wang, Yujun Li, Yewen Cao
2022 Mathematics  
Finally, the pre-trained language model Lawformer was used to provide knowledge for downstream tasks.  ...  The method proposed in this study achieved reasonably good performance in legal judgment prediction, which provides a promising solution for legal judgment prediction.  ...  In response to these problems, Xiao et al., proposed a Longformer-based pre-trained language model, Lawformer, in 2021 [18] .  ... 
doi:10.3390/math10132281 fatcat:eighmdktajh7fc77z473dd6twe

A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges [article]

Junyun Cui, Xiaoyu Shen, Feiping Nie, Zheng Wang, Jinglong Wang, Yulong Chen
2022 arXiv   pre-print
models in 3 languages and highlight 3 major research directions for LJP; (4) we show the state-of-art results for 8 representative datasets from different court cases and discuss the open challenges.  ...  and define a classification method of LJP with 3 different attributes; (2) we summarize 14 evaluation metrics under four categories for different outputs of LJP tasks; (3) we review 12 legal-domain pretrained  ...  Acknowledgment This work was supported in part by the Science Foundation of The China(Xi'an) Institute for Silk Road Research (2019YB05, and 2019YA07), the Innovation training project of Shaanxi college  ... 
arXiv:2204.04859v1 fatcat:gy75mpsh3ffj7b5b4tfoqfb444

LexGLUE: A Benchmark Dataset for Legal Language Understanding in English

Ilias Chalkidis, Abhik Jana, Dirk Hartung, Michael James Bommarito, Ion Androutsopoulos, Daniel Martin Katz, Nikolaos Aletras
2021 Social Science Research Network  
To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across a diverse  ...  Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors.  ...  The same applies to Lawformer , which was pre-trained on Chinese court opinions.  ... 
doi:10.2139/ssrn.3936759 fatcat:4rk7gscrp5edbjjqxqogn37oqa

LexGLUE: A Benchmark Dataset for Legal Language Understanding in English [article]

Ilias Chalkidis, Abhik Jana, Dirk Hartung, Michael Bommarito, Ion Androutsopoulos, Daniel Martin Katz, Nikolaos Aletras
2022 arXiv   pre-print
To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across a diverse  ...  Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors.  ...  Following Devlin et al. (2019) , and similarly to Hendrycks et al. (2021) , for each training (or test)  ... 
arXiv:2110.00976v3 fatcat:enmltnj7jngcvla5pxntmvw2bm

Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction [article]

Weijie Yu, Zhongxiang Sun, Jun Xu, Zhenhua Dong, Xu Chen, Hongteng Xu, Ji-Rong Wen
2022 arXiv   pre-print
This task has a high demand on the explainability of matching results because of its critical impacts on downstream applications – the matched legal cases may provide supportive evidence for the judgments  ...  As an essential operation of legal retrieval, legal case matching plays a central role in intelligent legal systems.  ...  conduct matching. 2) Lawformer [44] leverages a Longformer-based [4] pre-trained language model for Chinese legal long documents understanding. 3) BERT-PLI [41] uses BERT to capture paragraph-level  ... 
arXiv:2207.04182v1 fatcat:2oel57qo3bfrvhy2cixmjslpta

Translating Obligations: Tamassuk and Fārigh-khaṭṭī in the Indo-Persian World

Nandini Chatterjee
2021 Journal of the Economic and Social History of the Orient  
A necessarily widespread feature of language practice in the Persianate world was the need for translation of speech and text, with a range of lexical and semantic challenges involved in taking meaning  ...  This article focusses on legal translation, with its highly functional aims, by following the career of a pair of Indo-Persian legal forms known as tamassuk and fārigh-khaṭṭī, used for recording obligation  ...  I thank the participants of the 'Transactions and Documentation' workshop held in Exeter 2018, my colleagues on the Lawforms project, and the three anonymous reviewers, who helped me shape my arguments  ... 
doi:10.1163/15685209-12341546 fatcat:4clj7f26zjg4hd44ccfkiw6dni

Congestion and Delay in Asia's Courts

Jeffrey Falt
1985 UCLA Pacific Basin law journal  
, trained personnel and materiel resources. 2  ...  Case backlog and consequent delay in the disposition of disputes is a problem familiar to legal professionals the world over.  ...  Furthermore, more than two dozen languages are native to the Philippines. For most Filipinos, English is a second or third language. 256. M. Maceren, supra note 249, at 13-15. 257.  ... 
doi:10.5070/p841-2021923 fatcat:6lpiboyjpbezfpfkooudcra2ai

LexGLUE: A Benchmark Dataset for Legal Language Understanding in English

Ilias Chalkidis, Abhik Jana, Dirk Hartung, Michael Bommarito, Ion Androutsopoulos, Daniel Katz, Nikolaos Aletras
2022 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   unpublished
To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across a diverse  ...  Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors.  ...  Following Devlin et al. (2019) , and similarly to Hendrycks et al. (2021) , for each training (or test)  ... 
doi:10.18653/v1/2022.acl-long.297 fatcat:xggog6jkbzbxfekm627gg5j7mq

Survey on Efficient Training of Large Neural Networks

Julia Gusak, Daria Cherniuk, Alena Shilova, Alexandr Katrutsa, Daniel Bershatsky, Xunyi Zhao, Lionel Eyraud-Dubois, Oleh Shliazhko, Denis Dimitrov, Ivan Oseledets, Olivier Beaumont
2022 Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence   unpublished
Hence, many models don't fit one GPU device or can be trained using only a small per-GPU batch size.  ...  This survey provides a systematic overview of the approaches that enable more efficient DNNs training.  ...  Acknowledgments We thank the two anonymous reviewers for their helpful comments on an earlier draft of this paper.  ... 
doi:10.24963/ijcai.2022/765 fatcat:ph3boihxprb7jpcvvnlpwmd7vi