Contribution Analysis of Large Language Models and Data Augmentations for Person Names in Solving Legal Bar Examination at COLIEE 2023
Open Access
- 8 March 2024
- journal article
- research article
- Published by Springer Nature in The Review of Socionetwork Strategies
- Vol. 18 (1) , 123-143
Abstract
This paper describes our system for COLIEE 2023 Task 4, which automatically answers Japanese legal bar exam problems. We propose an extension to our previous system in COLIEE 2022, which achieved the highest accuracy among all submissions using data augmentation. We focus on problems that include mentions of person names. In this paper, we present two main contributions. First, we incorporate LUKE as our deep learning component, which is a named entity recognition model trained on RoBERTa. Second, we fine-tune the pretrained LUKE model in multiple ways, comparing fine-tuning on training datasets that include alphabetical person names and ensembling different fine-tuning models. We confirmed that LUKE and its fine-tuned model on person type problems improve their accuracies. Our formal run results show that LUKE and our fine-tuning approach using alphabetical person names were effective, achieving an accuracy of 0.69 in the COLIEE 2023 Task 4 formal run.Keywords
Funding Information
- KAKENHI (00271635, JP22H00804)
- Secom Science and Technology Foundation
This publication has 12 references indexed in Scilit:
- HUKB at the COLIEE 2022 Statute Law Task2023
- Using Textbook Knowledge for Statute Retrieval and Entailment Classification2023
- COLIEE 2022 Summary: Methods for Legal Document Retrieval and Entailment2023
- Overview and Discussion of the Competition on Legal Information Extraction/Entailment (COLIEE) 2021The Review of Socionetwork Strategies, 2022
- COLIEE 2020: Methods for Legal Document Retrieval and Entailment2021
- A Summary of the COLIEE 2019 Competition2020
- LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention2020
- Question Answering System for Legal Bar Examination Using Predicate Argument StructureLecture Notes in Computer Science, 2019
- COLIEE-2018: Evaluation of the Competition on Legal Information Extraction and Entailment2019
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks2019