Thesauri, which list the most salient semantic relations between words, have mostly been compiled manually. Therefore, the inclusion of an entry depends on the subjective decision of the lexicographer. As a consequence, those resources are usually incomplete. In this paper, we propose an unsupervised methodology to automatically discover pairs of semantically related words by highlighting their local environment and evaluating their semantic similarity in local and global semantic spaces. This proposal differs from all other research presented so far as it tries to take the best of two different methodologies, i.e. semantic space models and information extraction models. In particular, it can be applied to extract close semantic relations, it limits the search space to few, highly probable options and it is unsupervised.
This paper describes the HULTECH team participation in Task 3 of SemEval-2014. Four different subtasks are provided to the participants, who are asked to determine the semantic similarity of cross-level test pairs: paragraphto-sentence, sentence-to-phrase, phrase-toword and word-to-sense. Our system adopts a unified strategy (general purpose system) to calculate similarity across all subtasks based on word Web frequencies. For that purpose, we define ClueWeb InfoSimba, a cross-level similarity corpus-based metric. Results show that our strategy overcomes the proposed baselines and achieves adequate to moderate results when compared to other systems.
In order to automatically identify noun synonyms, we propose a new idea which opposes classical polysemous representations of words to monosemous 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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.