eprintid: 1890 rev_number: 13 eprint_status: archive userid: 43 dir: disk0/00/00/18/90 datestamp: 2013-11-13 15:00:42 lastmod: 2014-01-28 15:19:46 status_changed: 2013-11-13 15:00:42 type: book_section metadata_visibility: show contact_email: diego.ceccarelli@imtlucca.it creators_name: Ceccarelli, Diego creators_name: Lucchese, Claudio creators_name: Orlando, Salvatore creators_name: Perego, Raffaele creators_name: Trani, Salvatore creators_id: diego.ceccarelli@imtlucca.it creators_id: claudio.lucchese@isti.cnr.it creators_id: salvatore.orlando@isti.cnr.it creators_id: raffaele.perego@isti.cnr.it creators_id: salvatore.trani@isti.cnr.it title: Learning Relatedness Measures for Entity Linking ispublished: pub subjects: QA75 subjects: QA76 divisions: CSA full_text_status: public pres_type: speech keywords: Entity linking, relatedness measures, learning to rank abstract: Entity Linking is the task of detecting, in text documents, relevant mentions to entities of a given knowledge base. To this end, entity-linking algorithms use several signals and features extracted from the input text or from the knowl- edge base. The most important of such features is entity relatedness. Indeed, we argue that these algorithms benefit from maximizing the relatedness among the relevant enti- ties selected for annotation, since this minimizes errors in disambiguating entity-linking. The definition of an e↵ective relatedness function is thus a crucial point in any entity-linking algorithm. In this paper we address the problem of learning high-quality entity relatedness functions. First, we formalize the problem of learning entity relatedness as a learning-to-rank problem. We propose a methodology to create reference datasets on the basis of manually annotated data. Finally, we show that our machine-learned entity relatedness function performs better than other relatedness functions previously proposed, and, more importantly, improves the overall performance of dif- ferent state-of-the-art entity-linking algorithms. date: 2013-10-28 date_type: published publisher: ACM pagerange: 139-148 event_title: CIKM'13, 22nd ACM International Conference on Information and Knowledge Management event_location: San Francisco, CA, USA event_dates: 27-10-2013/1-11-2013 event_type: conference id_number: 10.1145/2505515.2505711 refereed: TRUE isbn: 978-1-4503-2263-8 book_title: Proceedings of the 22nd ACM international conference on Conference on information & knowledge management related_url_url: http://www.dxtr.it related_url_url: http://dexter.isti.cnr.it citation: Ceccarelli, Diego and Lucchese, Claudio and Orlando, Salvatore and Perego, Raffaele and Trani, Salvatore Learning Relatedness Measures for Entity Linking. In: Proceedings of the 22nd ACM international conference on Conference on information & knowledge management. ACM, pp. 139-148. ISBN 978-1-4503-2263-8 (2013) document_url: http://eprints.imtlucca.it/1890/1/paper.pdf