Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
NOVEL RANKING BASED LEXICAL SIMILARITY MEASURE FOR WORD EMBEDDING
Nov 03, 2017 (modified: Nov 03, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Distributional semantics models derive word space from linguistic items in context. Meaning is obtained by deﬁning a distance measure between vectors corresponding to lexical entities. Such vectors present several problems. In this paper we provide a guideline for post process improvements to the baseline vectors. We focus on reﬁning the similarity aspect, address imperfections of the model by applying the hubness reduction method, implementing relational knowledge into the model, and providing a new ranking similarity deﬁnition that give maximum weight to the top 1 component value. This feature ranking is similar to the one used in information retrieval. All these enrichments outperform any literature results so far for joint ESL and TOEF sets comparison. Since single word embedding is a basic element of any semantic tasks one can expect a signiﬁcant improvement of results for these tasks. Moreover, our improved method of text processingcanbetranslatedtocontinuousdistributedrepresentationofbiological sequences for deep proteomics and genomics.
TL;DR:NOVEL RANKING BASED LEXICAL SIMILARITY MEASURE FOR WORD EMBEDDING THAT GIVES STATE-OF-THE-ART RESULTS
Keywords:language models, vector spaces, word embedding, similarity
Enter your feedback below and we'll get back to you as soon as possible.