NOWJ1@ALQAC 2023: Enhancing Legal Task Performance with Classic Statistical Models and Pre-trained Language Models

TL;DR

This paper presents the NOWJ1 team's approach for ALQAC 2023, combining classical statistical models and pre-trained language models to improve legal document retrieval and question answering tasks, showing promising results.

Contribution

The paper introduces an integrated method using classical statistical models and PLMs for legal tasks, with specific techniques for document retrieval and question answering.

Findings

Effective pre-processing for input limitations

Successful application of learning-to-rank methods

Promising experimental results in legal QA

Abstract

This paper describes the NOWJ1 Team's approach for the Automated Legal Question Answering Competition (ALQAC) 2023, which focuses on enhancing legal task performance by integrating classical statistical models and Pre-trained Language Models (PLMs). For the document retrieval task, we implement a pre-processing step to overcome input limitations and apply learning-to-rank methods to consolidate features from various models. The question-answering task is split into two sub-tasks: sentence classification and answer extraction. We incorporate state-of-the-art models to develop distinct systems for each sub-task, utilizing both classic statistical models and pre-trained Language Models. Experimental results demonstrate the promising potential of our proposed methodology in the competition.