In this paper we present three unsupervised models for capturing discriminative attributes based on information from word embeddings, WordNet, and sentence-level word co-occurrence frequency. We show that, of these approaches, the simple approach based on word co-occurrence performs best. We further consider supervised and unsupervised approaches to combining information from these models, but these approaches do not improve on the word co-occurrence model.
CITATION STYLE
King, M., Parizi, A. H., & Cook, P. (2018). UNBNLP at SemEval-2018 Task 10: Evaluating unsupervised approaches to capturing discriminative attributes. In NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop (pp. 1013–1016). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/s18-1168
Mendeley helps you to discover research relevant for your work.