Multivariate Gaussian Document Representation from Word Embeddings for Text Categorization
作者： Giannis Nikolentzos , Polykarpos Meladianos , Francois Rousseau , Yannis Stavrakas , Michalis Vazirgiannis
DOI: 10.18653/V1/E17-2072
关键词:
摘要: Recently, there has been a lot of activity in learning distributed representations words vector spaces. Although are models capable high-quality words, how to generate the same quality for phrases or documents still remains challenge. In this paper, we propose model each document as multivariate Gaussian distribution based on its words. We then measure similarity between two their distributions. Experiments eight standard text categorization datasets demonstrate effectiveness proposed approach comparison with state-of-the-art methods.
aclweb.org参考文章(31)
Kilian Weinberger, Matt Kusner, Nicholas Kolkin, Yu Sun, From Word Embeddings To Document Distances international conference on machine learning. pp. 957- 966 ,(2015)
Rémi Lebret, Ronan Collobert, Word Embeddings through Hellinger PCA conference of the european chapter of the association for computational linguistics. pp. 482- 490 ,(2014) , 10.3115/V1/E14-1051
Roberto Zamparelli, Marco Baroni, Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space empirical methods in natural language processing. pp. 1183- 1193 ,(2010)
Ronan Collobert, Rémi Lebret, "The Sum of Its Parts": Joint Learning of Word and Phrase Representations with Autoencoders arXiv: Computation and Language. ,(2015)
Ronan Collobert, Remi Lebret, Remi Lebret, Pedro Pinheiro, Pedro Pinheiro, Phrase-based Image Captioning international conference on machine learning. pp. 2085- 2094 ,(2015)
Yoon Kim, Convolutional Neural Networks for Sentence Classification empirical methods in natural language processing. pp. 1746- 1751 ,(2014) , 10.3115/V1/D14-1181
David M Blei, Andrew Y Ng, Michael I Jordan, None, Latent dirichlet allocation Journal of Machine Learning Research. ,vol. 3, pp. 993- 1022 ,(2003) , 10.5555/944919.944937
Katrin Erk, Sebastian Padó, A structured vector space model for word meaning in context Proceedings of the Conference on Empirical Methods in Natural Language Processing - EMNLP '08. pp. 897- 906 ,(2008) , 10.3115/1613715.1613831
Xin Li Dan, Xin Li, Dan Roth, Learning question classifiers Proceedings of the 19th international conference on Computational linguistics -. pp. 1- 7 ,(2002) , 10.3115/1072228.1072378
Bernhard E. Boser, Isabelle M. Guyon, Vladimir N. Vapnik, A training algorithm for optimal margin classifiers conference on learning theory. pp. 144- 152 ,(1992) , 10.1145/130385.130401