Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Abstract

Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge. While promising, this approach requires to use models with billions of parameters, which are expensive to train and query. In this paper, we investigate how much these models can benefit from retrieving text passages, potentially containing evidence. We obtain state-of-the-art results on the Natural Questions and Triv-iaQA open benchmarks. Interestingly, we observe that the performance of this method significantly improves when increasing the number of retrieved passages. This is evidence that sequence-to-sequence models offers a flexible framework to efficiently aggregate and combine evidence from multiple passages.
Fichier principal
Vignette du fichier
Leveraging_Passage_Retrieval_with_Generative_Models__EACL_ (12).pdf (279.84 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03463108 , version 1 (02-12-2021)

Identifiers

Cite

Gautier Izacard, Edouard Grave. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2021, Kiev, Ukraine. pp.874-880, ⟨10.18653/v1/2021.eacl-main.74⟩. ⟨hal-03463108⟩
153 View
129 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More