Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong Park


Abstract
Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkable success. Yet, dense models require a vast amount of labeled training data for notable performance, whereas it is often challenging to acquire query-document pairs annotated by humans. To tackle this problem, we propose a simple but effective Document Augmentation for dense Retrieval (DAR) framework, which augments the representations of documents with their interpolation and perturbation. We validate the performance of DAR on retrieval tasks with two benchmark datasets, showing that the proposed DAR significantly outperforms relevant baselines on the dense retrieval of both the labeled and unlabeled documents.
Anthology ID:
2022.acl-short.48
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
442–452
Language:
URL:
https://aclanthology.org/2022.acl-short.48
DOI:
10.18653/v1/2022.acl-short.48
Bibkey:
Cite (ACL):
Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong Park. 2022. Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 442–452, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation (Jeong et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-short.48.pdf
Video:
 https://aclanthology.org/2022.acl-short.48.mp4
Code
 starsuzi/dar
Data
Natural QuestionsTriviaQA