Revisiting Word Embedding for Contrasting Meaning

Contrasting meaning is a basic aspect of semantics. Recent word-embedding models based on distributional semantics hypothesis are known to be weak for modeling lexical contrast. We present in this paper the embedding models that achieve an F-score of 92% on the widely-used, publicly available dataset, the GRE “most contrasting word” questions (Mohammad et al., 2008). This is the highest performance seen so far on this dataset. Surprisingly at the first glance, unlike what was suggested in most previous work, where relatedness statistics learned from corpora is claimed to yield extra gains over lexicon-based models, we obtained our best result relying solely on lexical resources (Roget’s and WordNet)—corpora statistics did not lead to further improvement. However, this should not be simply taken as that distributional statistics is not useful. We examine several basic concerns in modeling contrasting meaning to provide detailed analysis, with the aim to shed some light on the future directions for this basic semantics modeling problem.