NOVEL RANKING BASED LEXICAL SIMILARITY MEASURE FOR WORD EMBEDDING

Anonymous

Nov 03, 2017 (modified: Nov 03, 2017) ICLR 2018 Conference Blind Submission readers: everyone Show 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

Loading