Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

Query expansion with artificially generated texts

Vincent Claveau 1 
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : A well-known way to improve the performance of document retrieval is to expand the user's query. Several approaches have been proposed in the literature, and some of them are considered as yielding state-of-the-art results in IR. In this paper, we explore the use of text generation to automatically expand the queries. We rely on a well-known neural generative model, GPT-2, that comes with pre-trained models for English but can also be fine-tuned on specific corpora. Through different experiments, we show that text generation is a very effective way to improve the performance of an IR system, with a large margin (+10% MAP gains), and that it outperforms strong baselines also relying on query expansion (LM+RM3). This conceptually simple approach can easily be implemented on any IR system thanks to the availability of GPT code and models.
Complete list of metadata
Contributor : Vincent Claveau Connect in order to contact the contributor
Submitted on : Tuesday, November 16, 2021 - 12:20:41 PM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM

Links full text


  • HAL Id : hal-03430606, version 1
  • ARXIV : 2012.08787


Vincent Claveau. Query expansion with artificially generated texts. 2021. ⟨hal-03430606⟩



Record views