Factorization of latent variables in distributional semantic models
2015 (English)In: Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2015, 227-231 p.Conference paper (Refereed)Text
This paper discusses the use of factorization techniques in distributional semantic models. We focus on a method for redistributing the weight of latent variables, which has previously been shown to improve the performance of distributional semantic models. However, this result has not been replicated and remains poorly understood. We refine the method, and provide additional theoretical justification, as well as empirical results that demonstrate the viability of the proposed approach.
Place, publisher, year, edition, pages
Association for Computational Linguistics, 2015. 227-231 p.
Computational linguistics, Factorization, Semantics, Factorization techniques, Latent variable, Semantic Model, Natural language processing systems
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:kth:diva-187517ScopusID: 2-s2.0-84959933723ISBN: 9781941643327OAI: oai:DiVA.org:kth-187517DiVA: diva2:937001
Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, 17 September 2015 through 21 September 2015
QC 201606142016-06-142016-05-252016-06-14Bibliographically approved