Answering Legal Questions by Learning Neural Attentive Text Representation

Kien, Phi Manh; Nguyen, Ha-Thanh; Bach, Ngo Xuan; Tran, Vu; Nguyen, Minh Le; Phương, Từ Minh

doi:10.18653/v1/2020.coling-main.86

Cited by 32 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During our research on deep learning architectures, we found very simple architectures like SCNN [44], which have a small number of parameters that can still outperform other models. Interestingly, we also found the simple combination of CNN [35] architecture and attention mechanism [33] can give better results than bulky models in some specific cases. This chapter will answer the question of under what conditions can the end-to-end model perform well in a legal text processing task.…”

Section: Dissertation Outlinementioning

confidence: 75%

“…With the development of the internet and the explosion of digital data, methods of using machine learning [6,51], especially deep learning [20,59,33], are becoming more and more popular in NLP in general and automated legal processing in particular. Catering to this trend, a variety of datasets [68,25,19,72,36] and tasks [1,15,69,9] are introduced.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Toward Improving Attentive Neural Networks in Legal Text Processing

Nguyen¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In recent years, thanks to breakthroughs in neural network techniques especially attentive deep learning models, natural language processing has made many impressive achievements. However, automated legal word processing is still a difficult branch of natural language processing. Legal sentences are often long and contain complicated legal terminologies. Hence, models that work well on general documents still face challenges in dealing with legal documents. We have verified the existence of this problem with our experiments in this work. In this dissertation, we selectively present the main achievements in improving attentive neural networks in automatic legal document processing. Language models tend to grow larger and larger, though, without expert knowledge, these models can still fail in domain adaptation, especially for specialized fields like law.This dissertation has three main tasks to achieve the goal of improving attentive models in legal document processing. First, we survey and verify the factors affecting the performance of the models when operating on a specific domain such as law. This investigation is to provide clearer insights to improve models in this domain. Second, as pretrained language models are recently the most well-known attentive approaches in natural language processing, we provide methods to create language models specific to the legal domain, producing state-of-the-art results on reliable datasets. These models are built on features from the data of legal documents, with the goal of overcoming the challenges found in our previous survey. Third, besides the approach to let the model learn completely from raw data, we propose and prove the effectiveness of using different knowledge sources to inject into the model in different ways to adjust their output. This approach not only increases explainability but also allows humans to control pretrained language models and take advantage of the knowledge resources available during the development of the field such as vocabulary, grammar, logic and law.

show abstract

Section: Dissertation Outlinementioning

confidence: 75%

Section: Literature Reviewmentioning

confidence: 99%

Toward Improving Attentive Neural Networks in Legal Text Processing

Nguyen¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Binary Classification. Between the two U.S. datasets, although the Congressional bill survival prediction dataset [106] has a large number of samples, we selected Overruling [112] 1.1K French EU Y Retrieve related law articles for legal questions GerDaLIR [24] 123K German EU Y Precedent case search Kien et al [113] 5.9K Vietnamese VT N Retrieve related law articles for legal questions * Available upon request and/or under terms 1 https://casetext.com/blog/a-benchmark/ 2 https://www.sec.gov/ 3 https://sites.google.com/view/aila-2021/task-2-summarization-of-legal-judgements 4 https://sites.ualberta.ca/~rabelo/COLIEE2021/ [14] because the underlying task (deciding whether a given sentence overturns a precedent) could have more significant real-world impact. From the EU datasets, we chose Terms of Service rather than the ECHR dataset (cases from the European Court of Human Rights) [37] because we used two other datasets of court cases among the remaining tasks.…”

Section: A Dataset Selectionmentioning

confidence: 99%

On the Effectiveness of Pre-Trained Language Models for Legal Natural Language Processing: An Empirical Study

Song

Gao

et al. 2022

IEEE Access

View full text Add to dashboard Cite

We present the first comprehensive empirical evaluation of pre-trained language models (PLMs) for legal natural language processing (NLP) in order to examine their effectiveness in this domain.Our study covers eight representative and challenging legal datasets, ranging from 900 to 57K samples, across five NLP tasks: binary classification, multi-label classification, multiple choice question answering, summarization and information retrieval. We first run unsupervised, classical machine learning and/or non-PLM based deep learning methods on these datasets, and show that baseline systems' performance can be 4%∼35% lower than that of PLM-based methods. Next, we compare general-domain PLMs and those specifically pre-trained for the legal domain, and find that domain-specific PLMs demonstrate 1%∼5% higher performance than general-domain models, but only when the datasets are extremely close to the pretraining corpora. Finally, we evaluate six general-domain state-of-the-art systems, and show that they have limited generalizability to legal data, with performance gains from 0.1% to 1.2% over other PLM-based methods. Our experiments suggest that both general-domain and domain-specific PLM-based methods generally achieve better results than simpler methods on most tasks, with the exception of the retrieval task, where the best-performing baseline outperformed all PLM-based methods by at least 5%. Our findings can help legal NLP practitioners choose the appropriate methods for different tasks, and also shed light on potential future directions for legal NLP research.

show abstract

“…Among the latest published works in this family of methods, we can highlight the following: The Neural Attentive Text Representation from (Kien et al, 2020), the introduction of Few-shot Learning in the legal domain (Wu et al, 2020). Novel techniques for language modeling (Huang et al, 2020b).…”

Section: Ontology-based Solutionsmentioning

confidence: 99%

A Survey on Legal Question Answering Systems

Martinez‐Gil¹

2021

Preprint

View full text Add to dashboard Cite

Many legal professionals think that the explosion of information about local, regional, national, and international legislation makes their practice more costly, time-consuming, and even error-prone. The two main reasons for this are that most legislation is usually unstructured, and the tremendous amount and pace with which laws are released causes information overload in their daily tasks. In the case of the legal domain, the research community agrees that a system allowing to generate automatic responses to legal questions could substantially impact many practical implications in daily activities.The degree of usefulness is such that even a semi-automatic solution could significantly help to reduce the workload to be faced. This is mainly because a Question Answering system could be able to automatically process a massive amount of legal resources to answer a question or doubt in seconds, which means that it could save resources in the form of effort, money, and time to many professionals in the legal sector. In this work, we quantitatively and qualitatively survey the solutions that currently exist to meet this challenge.

show abstract

Answering Legal Questions by Learning Neural Attentive Text Representation

Cited by 32 publications

References 22 publications

Toward Improving Attentive Neural Networks in Legal Text Processing

Toward Improving Attentive Neural Networks in Legal Text Processing

On the Effectiveness of Pre-Trained Language Models for Legal Natural Language Processing: An Empirical Study

A Survey on Legal Question Answering Systems

Contact Info

Product

Resources

About