Spherere: Distinguishing lexical relations with hyperspherical relation embeddings

Lexical relations describe how meanings of terms relate to each other. Typical relations include hypernymy, synonymy, meronymy, etc. Automatic distinction of lexical relations is vital for NLP applications, and is also challenging due to the lack of contextual signals to discriminate between such relations. In this work, we present a neural representation learning model to distinguish lexical relations among term pairs based on Hyperspherical Relation Embeddings (SphereRE). Rather than learning embeddings for individual terms, the model learns representations of relation triples by mapping them to the hyperspherical embedding space, where relation triples of different lexical relations are well separated. We further introduce a Monte-Carlo based sampling and learning algorithm to train the model via transductive learning. Experiments over several benchmarks confirm SphereRE outperforms state-of-the-arts.