Relieving Polysemy Problem for Synonymy Detection

Abstract. In order to automatically identify noun synonyms, we propose a new idea which opposes classical polysemous representations of words to monose-mous representations based on the “one sense per discourse ” hypothesis. For that purpose, we apply the attributional similarity paradigm on two levels: corpus and document. We evaluate our methodology on well-known standard multiple choice synonymy question tests and evidence that it steadily outperforms the baseline.