Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

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

: Banerjee, Debayan; Chaudhuri, Debanjan; Dubey, Mohnish; Lehmann, Jens


Pan, J.Z.:
The Semantic Web - ISWC 2020. 19th International Semantic Web Conference. Proceedings. Pt.I : Athens, Greece, November 2-6, 2020
Cham: Springer Nature, 2020 (Lecture Notes in Computer Science 12506)
ISBN: 978-3-030-62418-7 (Print)
ISBN: 978-3-030-62419-4 (Online)
International Semantic Web Conference (ISWC) <19, 2020, Online>
Fraunhofer IAIS ()
Entity Linking; question answering; Knowledge Graphs; Wikidata

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.