Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation
arXiv:2105.00666
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.
arXiv commentSDP@NAACL2021
References in corpus (9)
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Document Expansion by Query Prediction
- Sparse, Dense, and Attentional Representations for Text Retrieval
- RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering
- Keyphrase Generation for Scientific Document Retrieval
- A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification
- Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization
- Query expansion with artificially generated texts
- Neural document expansion for ad-hoc information retrieval