Logo Logo
Help
Contact
Switch Language to German

Yaghoobzadeh, Yadollah and Schütze, Hinrich (October 2018): Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing. 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31. October - 04. November 2018. Riloff, Ellen; Chiang, David; Hockenmaier, Julia and Tsujii, Jun’ichi (eds.) : In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Stroudsburg PA: Association for Computational Linguistics. pp. 3060-3066 [PDF, 292kB]

[thumbnail of D18-1343.pdf]
Preview
Published Version
Download (292kB)

Abstract

Knowledge bases (KBs) are paramount in NLP. We employ multiview learning for increasing accuracy and coverage of entity type information in KBs. We rely on two metaviews: language and representation. For language, we consider high-resource and lowresource languages from Wikipedia. For representation, we consider representations based on the context distribution of the entity (i.e., on its embedding), on the entity’s name (i.e., on its surface form) and on its description in Wikipedia. The two metaviews language and representation can be freely combined: each pair of language and representation (e.g., German embedding, English description, Spanish name) is a distinct view. Our experiments on entity typing with fine-grained classes demonstrate the effectiveness of multiview learning. We release MVET, a large multiview – and, in particular, multilingual – entity typing dataset we created. Mono- and multilingual finegrained entity typing systems can be evaluated on this dataset.

Actions (login required)

View Item View Item