Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing

Yadollah Yaghoobzadeh, Hinrich Schütze
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
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
more » ... taviews 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.
doi:10.18653/v1/d18-1343 dblp:conf/emnlp/YaghoobzadehS18 fatcat:iz6le43puvb47feoswngprcjby