Lightning IR: Straightforward Fine-tuning and Inference of Transformer-based Language Models for Information 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_ | 1866910911412830208 |
|---|---|
| author | Schlatt, Ferdinand Fröbe, Maik Hagen, Matthias |
| author_facet | Schlatt, Ferdinand Fröbe, Maik Hagen, Matthias |
| contents | A wide range of transformer-based language models have been proposed for information retrieval tasks. However, including transformer-based models in retrieval pipelines is often complex and requires substantial engineering effort. In this paper, we introduce Lightning IR, an easy-to-use PyTorch Lightning-based framework for applying transformer-based language models in retrieval scenarios. Lightning IR provides a modular and extensible architecture that supports all stages of a retrieval pipeline: from fine-tuning and indexing to searching and re-ranking. Designed to be scalable and reproducible, Lightning IR is available as open-source: https://github.com/webis-de/lightning-ir. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04677 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lightning IR: Straightforward Fine-tuning and Inference of Transformer-based Language Models for Information Retrieval Schlatt, Ferdinand Fröbe, Maik Hagen, Matthias Information Retrieval A wide range of transformer-based language models have been proposed for information retrieval tasks. However, including transformer-based models in retrieval pipelines is often complex and requires substantial engineering effort. In this paper, we introduce Lightning IR, an easy-to-use PyTorch Lightning-based framework for applying transformer-based language models in retrieval scenarios. Lightning IR provides a modular and extensible architecture that supports all stages of a retrieval pipeline: from fine-tuning and indexing to searching and re-ranking. Designed to be scalable and reproducible, Lightning IR is available as open-source: https://github.com/webis-de/lightning-ir. |
| title | Lightning IR: Straightforward Fine-tuning and Inference of Transformer-based Language Models for Information Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2411.04677 |