UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings
Hypernym Discovery is the task of identifying potential hypernyms for a given term. A hypernym is a more generalized word that is super-ordinate to more specific words. This paper explores several approaches that rely on co-occurrence frequencies of word pairs, Hearst Patterns based on regular expressions, and word embeddings created from the UMBC corpus. Our system Babbage participated in Subtask 1A for English and placed 6th of 19 systems when identifying concept hypernyms, and 12th of 18 systems for entity hypernyms.
Paper
References (8)
06Vered Shwartz, Roberto Navigli, and Horacio Saggion2018 · Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018). Association for Computational Linguistics
07(c) Fetch IS-A Pattern from the input corpus and store as IS-A Corpus
08Applying word similarity to word embeddings: A fixed distance value called Phi (Fu et al., 2014) is used to extract words at this distance to the input term in the UMBC Embeddingour fi-nal