Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs

Résumé

Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extrac-tively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-IDF ranking. We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. We show that by linearizing the graph into a structured input sequence, models can encode the graph representations within a standard Sequence-to-Sequence setting. For two generative tasks with very long text input , long-form question answering and multi-document summarization, feeding graph representations as input can achieve better performance than using retrieved text portions.
Fichier principal
Vignette du fichier
output.pdf (1.45 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02277063 , version 1 (03-09-2019)

Licence

Domaine public

Identifiants

Citer

Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes. Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs. 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong Kong, China. ⟨10.18653/v1/D19-1428⟩. ⟨hal-02277063⟩
295 Consultations
466 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More