Skip to Main content Skip to Navigation
Conference papers

Apprendre des représentations jointes de mots et d'entités pour la désambiguïsation d'entités

Abstract : Combining Word and Entity Embeddings for Entity Linking. The correct identification of the link between an entity mention in a text and a known entity in a large knowledge base is important in information retrieval or information extraction. However, systems have to deal with ambiguity as numerous entities could be linked to a mention. This paper proposes a novel method for entity disambiguation which is based on the joint learning of embeddings for the words in the text and the entities in the knowledge base. By learning these embeddings in the same space we arrive at a more conceptually grounded model that can be used for candidate selection based on the surrounding context.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01626197
Contributor : Limsi Publications <>
Submitted on : Monday, November 13, 2017 - 1:03:09 PM
Last modification on : Wednesday, June 24, 2020 - 2:30:08 PM
Document(s) archivé(s) le : Wednesday, February 14, 2018 - 1:45:38 PM

File

taln2017desamb.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01626197, version 1

Citation

José Moreno, Romaric Besancon, Romain Beaumont, Eva d'Hondt, Anne-Laure Ligozat, et al.. Apprendre des représentations jointes de mots et d'entités pour la désambiguïsation d'entités. Conférence sur le Traitement Automatique des Langues Naturelles, Jan 2017, Orléans, France. ⟨hal-01626197⟩

Share

Metrics

Record views

276

Files downloads

250