Abstract
We describe a system for event extraction across documents and languages. We developed a framework for the interoperable semantic interpretation of mentions of events, participants, locations and time, as well as the relations between them. Furthermore, we use a common RDF model to represent instances of events and normalised entities and dates. We convert multiple mentions of the same event in English, Spanish and Dutch to a single representation. We thus resolve cross-document event and entity coreference within a language but also across languages. We tested our system on a Wikinews corpus of 120 English articles that have been manually translated to Spanish and Dutch. We report on the cross-lingual cross-document event and entity extraction comparing the Spanish and Dutch output with respect to English.
Cite
CITATION STYLE
Vossen, P., Laparra, E., Aldabe, I., & Rigau, G. (2015). Interoperability of cross-lingual and cross-document event detection. In NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation, EVENTS 2015 (pp. 108–116). Association for Computational Linguistics (ACL).
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.