Gradual Learning of Matrix-Space Models of Language for Sentiment Analysis

Aus International Center for Computational Logic
Wechseln zu:Navigation, Suche
Toggle side column

Gradual Learning of Matrix-Space Models of Language for Sentiment Analysis

Shima AsaadiShima Asaadi,  Sebastian RudolphSebastian Rudolph
Shima Asaadi, Sebastian Rudolph
Gradual Learning of Matrix-Space Models of Language for Sentiment Analysis
, August 2017. Proceedings of the 2nd Workshop on Representation Learning for NLP, ACL2017
  • KurzfassungAbstract
    Learning word representations to capture the semantics and compositionality of language has received much research interest in natural language processing. Beyond the popular vector space models, matrix representations for words have been proposed, since then, matrix multiplication can serve as natural composition operation. In this work, we investigate the problem of learning matrix representations of words. We present a learning approach for compositional matrix-space models for the task of sentiment analysis. We show that our approach, which learns the matrices gradually in two steps, outperforms other approaches and a gradient-descent baseline in terms of quality and computational cost.
  • Projekt:Project: QuantLA
  • Forschungsgruppe:Research Group: Computational Logic
@InProceedings{asaadi-rudolph:2017:RepL4NLP,
  author    = {Asaadi, Shima  and  Rudolph, Sebastian},
  title     = {Gradual Learning of Matrix-Space Models of Language for Sentiment Analysis},
  booktitle = {Proceedings of the 2nd Workshop on Representation Learning for NLP},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {178--185},
  abstract  = {Learning word representations to capture the semantics and compositionality of
	language has received much research interest in natural language processing.
	Beyond the popular vector space models, matrix representations for words have
	been proposed, since then, matrix multiplication can serve as natural
	composition operation. In this work, we investigate the problem of learning
	matrix representations of words. We present a learning approach for
	compositional matrix-space models for the task of sentiment analysis. We show
	that our approach, which learns the matrices gradually in two steps,
	outperforms other approaches and a gradient-descent baseline in terms of
	quality and computational cost.},
  url       = {http://www.aclweb.org/anthology/W17-2621}
}