Optimizing Multi-Stage Language Models for Effective Text Retrieval
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912170303815680 |
|---|---|
| author | Trung, Quang Hoang Hoang, Le Trung Phuc, Nguyen Van Hoang |
| author_facet | Trung, Quang Hoang Hoang, Le Trung Phuc, Nguyen Van Hoang |
| contents | Efficient text retrieval is critical for applications such as legal document analysis, particularly in specialized contexts like Japanese legal systems. Existing retrieval methods often underperform in such domain-specific scenarios, necessitating tailored approaches. In this paper, we introduce a novel two-phase text retrieval pipeline optimized for Japanese legal datasets. Our method leverages advanced language models to achieve state-of-the-art performance, significantly improving retrieval efficiency and accuracy. To further enhance robustness and adaptability, we incorporate an ensemble model that integrates multiple retrieval strategies, resulting in superior outcomes across diverse tasks. Extensive experiments validate the effectiveness of our approach, demonstrating strong performance on both Japanese legal datasets and widely recognized benchmarks like MS-MARCO. Our work establishes new standards for text retrieval in domain-specific and general contexts, providing a comprehensive solution for addressing complex queries in legal and multilingual environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19265 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing Multi-Stage Language Models for Effective Text Retrieval Trung, Quang Hoang Hoang, Le Trung Phuc, Nguyen Van Hoang Information Retrieval Computation and Language Machine Learning Efficient text retrieval is critical for applications such as legal document analysis, particularly in specialized contexts like Japanese legal systems. Existing retrieval methods often underperform in such domain-specific scenarios, necessitating tailored approaches. In this paper, we introduce a novel two-phase text retrieval pipeline optimized for Japanese legal datasets. Our method leverages advanced language models to achieve state-of-the-art performance, significantly improving retrieval efficiency and accuracy. To further enhance robustness and adaptability, we incorporate an ensemble model that integrates multiple retrieval strategies, resulting in superior outcomes across diverse tasks. Extensive experiments validate the effectiveness of our approach, demonstrating strong performance on both Japanese legal datasets and widely recognized benchmarks like MS-MARCO. Our work establishes new standards for text retrieval in domain-specific and general contexts, providing a comprehensive solution for addressing complex queries in legal and multilingual environments. |
| title | Optimizing Multi-Stage Language Models for Effective Text Retrieval |
| topic | Information Retrieval Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2412.19265 |