Abstract
One of the challenges in information retrieval (IR) is the vocabulary mismatch problem, which happens when the terms between queries and documents are lexically different but semantically similar. While recent work has proposed to expand the queries or documents by enriching their representations with additional relevant terms to address this challenge, they usually require a large volume of query-document pairs to train an expansion model. In this paper, we propose an Unsupervised Document Expansion with Generation (UDEG) framework with a pre-trained language model, which generates diverse supplementary sentences for the original document without using labels on query-document pairs for training. For generating sentences, we further stochastically perturb their embeddings to generate more diverse sentences for document expansion. We validate our framework on two standard IR benchmark datasets. The results show that our framework significantly outperforms relevant expansion baselines for IR.- Anthology ID:
- 2021.sdp-1.2
- Volume:
- Proceedings of the Second Workshop on Scholarly Document Processing
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- sdp
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7–17
- Language:
- URL:
- https://aclanthology.org/2021.sdp-1.2
- DOI:
- 10.18653/v1/2021.sdp-1.2
- Cite (ACL):
- Soyeong Jeong, Jinheon Baek, ChaeHun Park, and Jong Park. 2021. Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation. In Proceedings of the Second Workshop on Scholarly Document Processing, pages 7–17, Online. Association for Computational Linguistics.
- Cite (Informal):
- Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation (Jeong et al., sdp 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.sdp-1.2.pdf
- Code
- starsuzi/udeg
- Data
- MS MARCO