Skip to Main content Skip to Navigation
New interface
Conference papers

Génération de textes artificiels pour l'expansion de requêtes

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 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 : Saturday, October 23, 2021 - 12:01:52 AM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM


Files produced by the author(s)


  • HAL Id : hal-03398593, version 1


Vincent Claveau. Génération de textes artificiels pour l'expansion de requêtes. CORIA 2021 - Conférence en Recherche d’Information et Applications, Apr 2021, Grenoble, France. pp.1-16. ⟨hal-03398593⟩



Record views


Files downloads