Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing Année : 2021

Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs

Pawel Nowak
  • Fonction : Auteur
Francesco Piccinno
  • Fonction : Auteur
  • PersonId : 1216731

Résumé

We tackle the problem of weakly-supervised conversational Question Answering over large Knowledge Graphs using a neural semantic parsing approach. We introduce a new Logical Form (LF) grammar that can model a wide range of queries on the graph while remaining sufficiently simple to generate supervision data efficiently. Our Transformer-based model takes a JSON-like structure as input, allowing us to easily incorporate both Knowledge Graph and conversational contexts. This structured input is transformed to lists of embeddings and then fed to standard attention layers. We validate our approach, both in terms of grammar coverage and LF execution accuracy, on two publicly available datasets, CSQA and Con-vQuestions, both grounded in Wikidata. On CSQA, our approach increases the coverage from 80% to 96.2%, and the LF execution accuracy from 70.6% to 75.6%, with respect to previous state-of-the-art results. On ConvQuestions, we achieve competitive results with respect to the state-of-the-art.
Fichier principal
Vignette du fichier
main.pdf (819.24 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03944172 , version 1 (17-01-2023)

Licence

Identifiants

Citer

Pierre Marion, Pawel Nowak, Francesco Piccinno. Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, pp.8813-8829. ⟨10.18653/v1/2021.emnlp-main.695⟩. ⟨hal-03944172⟩
15 Consultations
19 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More