Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

TL;DR

This paper introduces an unsupervised framework that uses stochastic text generation with pre-trained language models to expand documents for improved information retrieval, effectively addressing vocabulary mismatch without labeled data.

Contribution

The proposed UDEG framework generates diverse supplementary sentences for document expansion using stochastic perturbations, eliminating the need for query-document pair labels.

Findings

Significantly outperforms baseline expansion methods on IR benchmarks.

Effective in addressing vocabulary mismatch in information retrieval.

Demonstrates the potential of unsupervised generation for IR enhancement.

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.