DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917629445275648 |
|---|---|
| author | Chandradevan, Ramraj Dhole, Kaustubh D. Agichtein, Eugene |
| author_facet | Chandradevan, Ramraj Dhole, Kaustubh D. Agichtein, Eugene |
| contents | State-of-the-art neural rankers pre-trained on large task-specific training data such as MS-MARCO, have been shown to exhibit strong performance on various ranking tasks without domain adaptation, also called zero-shot. However, zero-shot neural ranking may be sub-optimal, as it does not take advantage of the target domain information. Unfortunately, acquiring sufficiently large and high quality target training data to improve a modern neural ranker can be costly and time-consuming. To address this problem, we propose a new approach to unsupervised domain adaptation for ranking, DUQGen, which addresses a critical gap in prior literature, namely how to automatically generate both effective and diverse synthetic training data to fine tune a modern neural ranker for a new domain. Specifically, DUQGen produces a more effective representation of the target domain by identifying clusters of similar documents; and generates a more diverse training dataset by probabilistic sampling over the resulting document clusters. Our extensive experiments, over the standard BEIR collection, demonstrate that DUQGen consistently outperforms all zero-shot baselines and substantially outperforms the SOTA baselines on 16 out of 18 datasets, for an average of 4% relative improvement across all datasets. We complement our results with a thorough analysis for more in-depth understanding of the proposed method's performance and to identify promising areas for further improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02489 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation Chandradevan, Ramraj Dhole, Kaustubh D. Agichtein, Eugene Information Retrieval Computation and Language State-of-the-art neural rankers pre-trained on large task-specific training data such as MS-MARCO, have been shown to exhibit strong performance on various ranking tasks without domain adaptation, also called zero-shot. However, zero-shot neural ranking may be sub-optimal, as it does not take advantage of the target domain information. Unfortunately, acquiring sufficiently large and high quality target training data to improve a modern neural ranker can be costly and time-consuming. To address this problem, we propose a new approach to unsupervised domain adaptation for ranking, DUQGen, which addresses a critical gap in prior literature, namely how to automatically generate both effective and diverse synthetic training data to fine tune a modern neural ranker for a new domain. Specifically, DUQGen produces a more effective representation of the target domain by identifying clusters of similar documents; and generates a more diverse training dataset by probabilistic sampling over the resulting document clusters. Our extensive experiments, over the standard BEIR collection, demonstrate that DUQGen consistently outperforms all zero-shot baselines and substantially outperforms the SOTA baselines on 16 out of 18 datasets, for an average of 4% relative improvement across all datasets. We complement our results with a thorough analysis for more in-depth understanding of the proposed method's performance and to identify promising areas for further improvements. |
| title | DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2404.02489 |