Improving Vietnamese Legal Question--Answering System based on Automatic Data Enrichment
This addresses legal QA for low-resource Vietnamese, though it appears incremental as it focuses on data enrichment rather than a fundamental breakthrough.
The paper tackles the challenge of Vietnamese legal question answering by implementing an article-level retrieval-based system and introducing a novel weak labeling method for data enrichment, resulting in improved performance where labeled data is limited.
Question answering (QA) in law is a challenging problem because legal documents are much more complicated than normal texts in terms of terminology, structure, and temporal and logical relationships. It is even more difficult to perform legal QA for low-resource languages like Vietnamese where labeled data are rare and pre-trained language models are still limited. In this paper, we try to overcome these limitations by implementing a Vietnamese article-level retrieval-based legal QA system and introduce a novel method to improve the performance of language models by improving data quality through weak labeling. Our hypothesis is that in contexts where labeled data are limited, efficient data enrichment can help increase overall performance. Our experiments are designed to test multiple aspects, which demonstrate the effectiveness of the proposed technique.