PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909133320486912 |
|---|---|
| author | Dadas, Sławomir Perełkiewicz, Michał Poświata, Rafał |
| author_facet | Dadas, Sławomir Perełkiewicz, Michał Poświata, Rafał |
| contents | We present Polish Information Retrieval Benchmark (PIRB), a comprehensive evaluation framework encompassing 41 text information retrieval tasks for Polish. The benchmark incorporates existing datasets as well as 10 new, previously unpublished datasets covering diverse topics such as medicine, law, business, physics, and linguistics. We conduct an extensive evaluation of over 20 dense and sparse retrieval models, including the baseline models trained by us as well as other available Polish and multilingual methods. Finally, we introduce a three-step process for training highly effective language-specific retrievers, consisting of knowledge distillation, supervised fine-tuning, and building sparse-dense hybrid retrievers using a lightweight rescoring model. In order to validate our approach, we train new text encoders for Polish and compare their results with previously evaluated methods. Our dense models outperform the best solutions available to date, and the use of hybrid methods further improves their performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13350 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods Dadas, Sławomir Perełkiewicz, Michał Poświata, Rafał Computation and Language We present Polish Information Retrieval Benchmark (PIRB), a comprehensive evaluation framework encompassing 41 text information retrieval tasks for Polish. The benchmark incorporates existing datasets as well as 10 new, previously unpublished datasets covering diverse topics such as medicine, law, business, physics, and linguistics. We conduct an extensive evaluation of over 20 dense and sparse retrieval models, including the baseline models trained by us as well as other available Polish and multilingual methods. Finally, we introduce a three-step process for training highly effective language-specific retrievers, consisting of knowledge distillation, supervised fine-tuning, and building sparse-dense hybrid retrievers using a lightweight rescoring model. In order to validate our approach, we train new text encoders for Polish and compare their results with previously evaluated methods. Our dense models outperform the best solutions available to date, and the use of hybrid methods further improves their performance. |
| title | PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.13350 |