Improving neural entity disambiguation with graph embeddings

Özge Sevgili, Alexander Panchenko, Chris Biemann

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    19 Citations (Scopus)

    Abstract

    Entity Disambiguation (ED) is the task of linking an ambiguous entity mention to a corresponding entry in a knowledge base. Current methods have mostly focused on unstructured text data to learn representations of entities, however, there is structured information in the knowledge base itself that should be useful to disambiguate entities. In this work, we propose a method that uses graph embeddings for integrating structured information from the knowledge base with unstructured information from text-based representations. Our experiments confirm that graph embeddings trained on a graph of hyperlinks between Wikipedia articles improve the performances of simple feed-forward neural ED model and a state-ofthe- art neural ED system.

    Original languageEnglish
    Title of host publicationACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Student Research Workshop
    PublisherAssociation for Computational Linguistics (ACL)
    Pages315-322
    Number of pages8
    ISBN (Electronic)9781950737475
    Publication statusPublished - 2019
    Event57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Student Research Workshop, SRW 2019 - Florence, Italy
    Duration: 28 Jul 20192 Aug 2019

    Publication series

    NameACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Student Research Workshop

    Conference

    Conference57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Student Research Workshop, SRW 2019
    Country/TerritoryItaly
    CityFlorence
    Period28/07/192/08/19

    Fingerprint

    Dive into the research topics of 'Improving neural entity disambiguation with graph embeddings'. Together they form a unique fingerprint.

    Cite this