Combining Discourse Markers and Cross-lingual Embeddings for Synonym–Antonym Classification

It is well-known that distributional semantic approaches have difficulty in distinguishing between synonyms and antonyms (Grefenstette, 1992; Pado and Lapata, 2003). Recent work has shown that supervision available in English for this task (e.g., lexical resources) can be transferred to other languages via cross-lingual word embeddings. However, this kind of transfer misses monolingual distributional information available in a target language, such as contrast relations that are indicative of antonymy (e.g., hot...while...cold). In this work, we improve the transfer by exploiting monolingual information, expressed in the form of co-occurrences with discourse markers that convey contrast. Our approach makes use of less than a dozen markers, which can easily be obtained for many languages. Compared to a baseline using only cross-lingual embeddings, we show absolute improvements of 410% F-1-score in Vietnamese and Hindi.