PNEL: Pointer Network Based End-To-End Entity Linking over Knowledge Graphs

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

Question Answering systems are generally modelled as a pipeline consisting of a sequence of steps. In such a pipeline, Entity Linking (EL) is often the first step. Several EL models first perform span detection and then entity disambiguation. In such models errors from the span detection phase cascade to later steps and result in a drop of overall accuracy. Moreover, lack of gold entity spans in training data is a limiting factor for span detector training. Hence the movement towards end-to-end EL models began where no separate span detection step is involved. In this work we present a novel approach to end-to-end EL by applying the popular Pointer Network model, which achieves competitive performance. We demonstrate this in our evaluation over three datasets on the Wikidata Knowledge Graph.

Original languageEnglish
Title of host publicationThe Semantic Web – ISWC 2020 - 19th International Semantic Web Conference, 2020, Proceedings
EditorsJeff Z. Pan, Valentina Tamma, Claudia d’Amato, Krzysztof Janowicz, Bo Fu, Axel Polleres, Oshani Seneviratne, Lalana Kagal
Number of pages18
Volume1
Place of PublicationCham
PublisherSpringer Science and Business Media Deutschland GmbH
Publication date2020
Pages21-38
ISBN (print)978-3-030-62418-7
ISBN (electronic)978-3-030-62419-4
DOIs
Publication statusPublished - 2020
Externally publishedYes
Event19th International Semantic Web Conference - ISWC 2020 - Virtual Conference, Athens, Greece
Duration: 01.11.202006.11.2020
Conference number: 19
https://iswc2020.semanticweb.org/

Bibliographical note

Publisher Copyright:
© 2020, Springer Nature Switzerland AG.

    Research areas

  • Entity Linking, Knowledge Graphs, Question Answering, Wikidata
  • Informatics