Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

Soyeong Jeong, Jinheon Baek, ChaeHun Park, Jong Park


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
Editors:
Iz Beltagy, Arman Cohan, Guy Feigenblat, Dayne Freitag, Tirthankar Ghosal, Keith Hall, Drahomira Herrmannova, Petr Knoth, Kyle Lo, Philipp Mayr, Robert M. Patton, Michal Shmueli-Scheuer, Anita de Waard, Kuansan Wang, Lucy Lu Wang
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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2021.sdp-1.2.pdf
Code
 starsuzi/udeg
Data
MS MARCO