Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing
This work addresses entity typing for NLP applications, offering a multilingual dataset for evaluation, but it is incremental as it builds on existing multiview learning techniques.
The paper tackles the problem of improving entity typing accuracy and coverage in knowledge bases by using multiview learning that combines multiple languages and representations, and it demonstrates effectiveness on fine-grained entity typing experiments.
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 low-resource 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 fine-grained entity typing systems can be evaluated on this dataset.