Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Résumé

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
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

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

Identifiants

Citer

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⟩
140 Consultations
121 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More