Abstract
Despite the recent advancements in information retrieval (IR), zero-shot IR remains a significant challenge, especially when dealing with new domains, languages, and newly-released use cases that lack historical query traffic from existing users. For such cases, it is common to use query augmentations followed by fine-tuning pre-trained models on the document data paired with synthetic queries. In this work, we propose a novel Universal Document Linking (UDL) algorithm, which links similar documents to enhance synthetic query generation across multiple datasets with different characteristics. UDL leverages entropy for the choice of similarity models and named entity recognition (NER) for the link decision of documents using similarity scores. Our empirical studies demonstrate the effectiveness and universality of the UDL across diverse datasets and IR models, surpassing state-of-the-art methods in zero-shot cases. The developed code for reproducibility is included in https://github.com/eoduself/UDL- Anthology ID:
- 2024.emnlp-main.1056
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 18971–18982
- Language:
- URL:
- https://aclanthology.org/2024.emnlp-main.1056
- DOI:
- 10.18653/v1/2024.emnlp-main.1056
- Cite (ACL):
- Dae Yon Hwang, Bilal Taha, Harshit Pande, and Yaroslav Nechaev. 2024. Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18971–18982, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval (Hwang et al., EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.emnlp-main.1056.pdf