Log In Sign Up

Query Expansion Using Contextual Clue Sampling with Language Models

by   Linqing Liu, et al.

Query expansion is an effective approach for mitigating vocabulary mismatch between queries and documents in information retrieval. One recent line of research uses language models to generate query-related contexts for expansion. Along this line, we argue that expansion terms from these contexts should balance two key aspects: diversity and relevance. The obvious way to increase diversity is to sample multiple contexts from the language model. However, this comes at the cost of relevance, because there is a well-known tendency of models to hallucinate incorrect or irrelevant contexts. To balance these two considerations, we propose a combination of an effective filtering strategy and fusion of the retrieved documents based on the generation probability of each context. Our lexical matching based approach achieves a similar top-5/top-20 retrieval accuracy and higher top-100 accuracy compared with the well-established dense retrieval model DPR, while reducing the index size by more than 96 method and achieves the highest Exact-Match score against several competitive baselines.


page 1

page 2

page 3

page 4


Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

One of the challenges in information retrieval (IR) is the vocabulary mi...

Deep Neural Networks for Query Expansion using Word Embeddings

Query expansion is a method for alleviating the vocabulary mismatch prob...

A Vertical PRF Architecture for Microblog Search

In microblog retrieval, query expansion can be essential to obtain good ...

Generation-Augmented Retrieval for Open-domain Question Answering

Conventional sparse retrieval methods such as TF-IDF and BM25 are simple...

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

Pseudo-relevance feedback (PRF) has proven to be an effective query refo...

IntenT5: Search Result Diversification using Causal Language Models

Search result diversification is a beneficial approach to overcome under...

Attention-Based Query Expansion Learning

Query expansion is a technique widely used in image search consisting in...