Our long conference paper titled “Querying Word Embeddings for Similarity and Relatedness” has been accepted for presentation at the NAACL 2018. If you have been using word embeddings without knowing the mechanism of obtaining them in an unsupervised approach using co-occurrence data, this talk will surprise you.
Abstract: Word embeddings obtained from neural network models such as Wor2Vec Skipgram have become popular representations of word meaning and have been evaluated on a variety of word similarity and relatedness norming data. Skipgram generates a set of word and context embeddings, the latter typically discarded after training. We demonstrate the usefulness of context embeddings in predicting asymmetric association between words from a recently published dataset of production norms (Jouravlev & McRae, 2016). Our findings suggest that humans respond with words closer to the cue within the context embedding space (rather than the word embedding space), when asked to generate thematically related words.