A Cross-Lingual Statutory Article Retrieval Dataset for Taiwan Legal Studies

Yen-Hsiang Wang, Feng-Dian Su, Tzu-Yu Yeh, Yao-Chung Fan
10/15/2024
cs.CL

No official code found. Best implementation: NCHU-NLP-Lab/LawFactsQA-TW (7 stars, last commit 2024-10-16).

Abstract

This paper introduces a cross-lingual statutory article retrieval (SAR) dataset designed to enhance legal information retrieval in multilingual settings. Our dataset features spoken-language-style legal inquiries in English, paired with corresponding Chinese versions and relevant statutes, covering all Taiwanese civil, criminal, and administrative laws. This dataset aims to improve access to legal information for non-native speakers, particularly for foreign nationals in Taiwan. We propose several LLM-based methods as baselines for evaluating retrieval effectiveness, focusing on mitigating translation errors and improving cross-lingual retrieval performance. Our work provides a valuable resource for developing inclusive legal information retrieval systems.

View on arXivView PDF

Code Implementations(1)

NCHU-NLP-Lab/LawFactsQA-TWCommunity100%
72PythonAug 29, 20242 years ago

Similar Papers

LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval

82% match1 repo12025

Optimizing Multi-Stage Language Models for Effective Text Retrieval

82% match2024

Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval

80% match1 repo12024

DeliLaw: A Chinese Legal Counselling System Based on a Large Language Model

80% match2024

LRAGE: Legal Retrieval Augmented Generation Evaluation Tool

80% match1 repo772025

STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals

80% match1 repo252024

Cite this paper

@article{wang2024crosslingual,
  title  = {A Cross-Lingual Statutory Article Retrieval Dataset for Taiwan Legal Studies},
  author = {Yen-Hsiang Wang and Feng-Dian Su and Tzu-Yu Yeh and Yao-Chung Fan},
  year   = {2024},
  eprint = {2410.11450},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.11450v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.11450.svg)](https://codeofpaper.com/paper/2410.11450)

Discussion