⚖️ A Statutory Article Retrieval Dataset in French.

Last update: Nov 17, 2022

Overview

A Statutory Article Retrieval Dataset in French

This repository contains the Belgian Statutory Article Retrieval Dataset (BSARD), as well as the code to reproduce the experimental results from the associated paper by A. Louis, G. Spanakis, and G. Van Dijck.

Abstract. Statutory article retrieval is the task of automatically retrieving law articles relevant to a legal question. While recent advances in natural language processing have sparked considerable interest in many legal tasks, statutory article retrieval remains primarily untouched due to the scarcity of large-scale and high-quality annotated datasets. To address this bottleneck, we introduce the Belgian Statutory Article Retrieval Dataset (BSARD), which consists of 1,100+ French native legal questions labeled by experienced jurists with relevant articles from a corpus of 22,600+ Belgian law articles. Using BSARD, we benchmark several unsupervised information retrieval methods based on term weighting and pooled embeddings. Our best performing baseline achieves 50.8% [email protected], which is promising for the feasibility of the task and indicates that there is still substantial room for improvement. By the specificity of the data domain and addressed task, BSARD presents a unique challenge problem for future research on legal information retrieval.

Documentation

Detailed documentation on the dataset and how to reproduce the main experimental results can be found here.

Citation

For attribution in academic contexts, please cite this work as:

@article{louis2021statutory,
  title = {A Statutory Article Retrieval Dataset in French},
  author = {Louis, Antoine and Spanakis, Gerasimos and Van Dijck, Gijs},
  journal = {arXiv preprint arXiv:2108.11792},
  year = {2021},
}

License

This repository is licensed under the terms of the CC BY-NC-SA 4.0 license.

You might also like...

🏆 The 1st Place Submission to AICity Challenge 2021 Natural Language-Based Vehicle Retrieval Track (Alibaba-UTS submission)

26 Apr 29, 2021

Code for papers "Generation-Augmented Retrieval for Open-Domain Question Answering" and "Reader-Guided Passage Reranking for Open-Domain Question Answering", ACL 2021

This repo provides the code of the following papers: (GAR) "Generation-Augmented Retrieval for Open-domain Question Answering", ACL 2021 (RIDER) "Read

49 Dec 26, 2022

Composed Image Retrieval using Pretrained LANguage Transformers (CIRPLANT)

CIRPLANT This repository contains the code and pre-trained models for Composed Image Retrieval using Pretrained LANguage Transformers (CIRPLANT) For d

29 Nov 17, 2022

[ICCV 2021] Instance-level Image Retrieval using Reranking Transformers

Instance-level Image Retrieval using Reranking Transformers Fuwen Tan, Jiangbo Yuan, Vicente Ordonez, ICCV 2021. Abstract Instance-level image retriev

86 Dec 28, 2022

Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation Official Code Repository for the paper "Unsupervised Documen

2 Oct 26, 2021

Question and answer retrieval in Turkish with BERT

trfaq Google supported this work by providing Google Cloud credit. Thank you Google for supporting the open source! 🎉 What is this? At this repo, I'm

13 Oct 10, 2022

Legal text retrieval for python

legal-text-retrieval Overview This system contains 2 steps: generate training data containing negative sample found by mixture score of cosine(tfidf)

22 Dec 6, 2022

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

Memorizing Transformers - Pytorch Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memori

364 Jan 6, 2023

Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.

textgenrnn Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code, or quickly tr

4.8k Dec 30, 2022

Comments

transformers library version should be specified

Hi,

As specified in the documentation, I made the environment from the yml file: time conda env create -n bsard -f environment.yml

However, I run into an error when doing the grid search:

Traceback (most recent call last):                                                                                                                                                   
  File "scripts/search_hyperparameters.py", line 11, in <module>
    from retriever import Word2vecRetriever, FasttextRetriever, BERTRetriever
  File "/u/salaunol/Documents/_2021_automne/bsard/scripts/retriever.py", line 16, in <module>
    from transformers import (CamembertModel, CamembertTokenizer,
ImportError: cannot import name 'CamembertModel' from 'transformers' (/u/salaunol/anaconda3/envs/bsard/lib/python3.8/site-packages/transformers/__init__.py)

The transformers version was the following: transformers 2.1.1 pyhd3eb1b0_0

I fixed it with pip install transformers==2.5.0 but it would be preferable to specify the version for each library in environment.yml

Edit: issue submitted too fast

opened by oliviersalaun 1

Releases(v1.0)

v1.0(Aug 26, 2021)

The Belgian Statutory Article Retrieval Dataset (BSARD) v1.0 is a French native corpus for studying statutory article retrieval. BSARD consists of more than 22,600 statutory articles from Belgian law and about 1,100 legal questions posed by Belgian citizens and labeled by experienced jurists with relevant articles from the corpus.
Source code(tar.gz)
Source code(zip)

Owner

Maastricht Law & Tech Lab

The Lab aims to offer innovative education and to build a creative community of researchers at the intersections of law, technology and data science.

GitHub Repository

Recognition of 38 speech commands in russian. Based on Yandex Cup 2021 ML Challenge: ASR

Speech_38_ru_commands Recognition of 38 speech commands in russian. Based on Yandex Cup 2021 ML Challenge: ASR Программа умеет распознавать 38 ключевы

9 May 05, 2022

【原神】自动演奏风物之诗琴的程序

疯物之诗琴读取midi并自动演奏原神风物之诗琴。可以自定义配置文件自动调整音符来适配风物之诗琴。（原神1.4直播那天就开始做了！到现在才能放出来。。）如何使用在Release页面中下载打包好的程序和midi压缩包并解压。双击运行“疯物之诗琴.exe”。在原神中打开风物之诗琴，软件内输入

435 Jan 04, 2023

Vad-sli-asr - A Python scripts for a speech processing pipeline with Voice Activity Detection (VAD)

VAD-SLI-ASR Python scripts for a speech processing pipeline with Voice Activity

14 Dec 09, 2022

NumPy String-Indexed is a NumPy extension that allows arrays to be indexed using descriptive string labels

NumPy String-Indexed NumPy String-Indexed is a NumPy extension that allows arrays to be indexed using descriptive string labels, rather than conventio

1 Jan 08, 2022

This is the source code of RPG (Reward-Randomized Policy Gradient)

RPG (Reward-Randomized Policy Gradient) Zhenggang Tang*, Chao Yu*, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu (

40 Nov 25, 2022

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

CRNN paper：An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition 1. create your ow

3 Apr 02, 2022

⚖️ A Statutory Article Retrieval Dataset in French.

Related tags

Overview

A Statutory Article Retrieval Dataset in French

Documentation

Citation

License

You might also like...

🏆 The 1st Place Submission to AICity Challenge 2021 Natural Language-Based Vehicle Retrieval Track (Alibaba-UTS submission)

Code for papers "Generation-Augmented Retrieval for Open-Domain Question Answering" and "Reader-Guided Passage Reranking for Open-Domain Question Answering", ACL 2021

Composed Image Retrieval using Pretrained LANguage Transformers (CIRPLANT)

[ICCV 2021] Instance-level Image Retrieval using Reranking Transformers

Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

Question and answer retrieval in Turkish with BERT

Legal text retrieval for python

Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate nearest neighbors, in Pytorch

Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.

Comments

transformers library version should be specified

Releases(v1.0)

v1.0(Aug 26, 2021)

Owner

Maastricht Law & Tech Lab

Recognition of 38 speech commands in russian. Based on Yandex Cup 2021 ML Challenge: ASR

【原神】自动演奏风物之诗琴的程序

Vad-sli-asr - A Python scripts for a speech processing pipeline with Voice Activity Detection (VAD)

NumPy String-Indexed is a NumPy extension that allows arrays to be indexed using descriptive string labels

This is the source code of RPG (Reward-Randomized Policy Gradient)

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

CCF BDCI BERT系统调优赛题baseline（Pytorch版本）

RIDE automatically creates the package and boilerplate OOP Python node scripts as per your needs

Implementation of ProteinBERT in Pytorch

This repository describes our reproducible framework for assessing self-supervised representation learning from speech

The swas programming language

Graphical user interface for Argos Translate

An A-SOUL Text Generator Based on CPM-Distill.

fastai ulmfit - Pretraining the Language Model, Fine-Tuning and training a Classifier

novel deep learning research works with PaddlePaddle

A collection of models for image - text generation in ACM MM 2021.

Leon is an open-source personal assistant who can live on your server.

Train 🤗transformers with DeepSpeed: ZeRO-2, ZeRO-3

Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision

Converts python code into c++ by using OpenAI CODEX.