Neural text generation for query expansion in information retrieval - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Neural text generation for query expansion in information retrieval

Abstract

Expanding users' query is a well-known way to improve the performance of document retrieval systems. Several approaches have been proposed in the literature, and some of them are considered as yielding state-of-the-art results in Information Retrieval. In this paper, we explore the use of text generation to automatically expand the queries. We rely on a well-known neural generative model, OpenAI's GPT-2, that comes with pre-trained models for English but can also be fine-tuned on specific corpora. Through different experiments and several datasets, 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 (RM3). This conceptually simple approach can easily be implemented on any IR system thanks to the availability of GPT code and models.
Fichier principal
Vignette du fichier
Claveau_GPT4IR_WI2021.pdf (603.65 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03494692 , version 1 (21-12-2021)

Identifiers

Cite

Vincent Claveau. Neural text generation for query expansion in information retrieval. WI-IAT 2021 - 20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Dec 2021, Melbourne, Australia. pp.1-8, ⟨10.1145/3486622.3493957⟩. ⟨hal-03494692⟩
132 View
378 Download

Altmetric

Share

Gmail Facebook X LinkedIn More