Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible
Abhijeet Gupta, Gemma Boleda, Sebastian Padó · 2017
Word embeddings are supposed to provide easy access to semantic relations such as "male of" (man-woman).While this claim has been investigated for concepts, little is known about the distributional behavior of relations of (Named) Entities.We describe two word embedding-based models that predict values for relational attributes of entities, and analyse them.The task is challenging, with major performance differences between relations.Contrary to many NLP tasks, high difficulty for a relation does not result from low frequency, but from (a) one-to-many mappings; and (b) lack of context patterns expressing the relation that are easy to pick up by word embeddings.