Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples. - Archive ouverte HAL
Article Dans Une Revue Journal of Web Semantics Année : 2018

Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples.

Lucie-Aimée Kaffee
  • Fonction : Auteur
  • PersonId : 1031484
Christophe Gravier
Frederique Laforest

Résumé

Most people need textual or visual interfaces in order to make sense of Semantic Web data. In this paper, we investigate the problem of generating natural language summaries for Semantic Web data using neural networks. Our end-to-end trainable architecture encodes the information from a set of triples into a vector of fixed dimensionality and generates a textual summary by conditioning the output on the encoded vector. W e explore a set of different approaches that enable our models to verbalise entities from the input set of triples in the generated text. Our systems are trained and evaluated on two corpora of loosely aligned Wikipedia snippets with triples from DBpedia and Wikidata, with promising results

Dates et versions

hal-01915935 , version 1 (08-11-2018)

Identifiants

Citer

Pavlos Vougiouklis, Hady Elsahar, Lucie-Aimée Kaffee, Christophe Gravier, Frederique Laforest, et al.. Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples.. Journal of Web Semantics, 2018, 52-53, pp.1-15. ⟨10.1016/j.websem.2018.07.002⟩. ⟨hal-01915935⟩
56 Consultations
0 Téléchargements

Altmetric

Partager

More