Multivariate Gaussian Document Representation from Word Embeddings for Text Categorization

Giannis Nikolentzos, Polykarpos Meladianos, François Rousseau, Yannis Stavrakas, Michalis Vazirgiannis


Abstract
Recently, there has been a lot of activity in learning distributed representations of words in vector spaces. Although there are models capable of learning high-quality distributed representations of words, how to generate vector representations of the same quality for phrases or documents still remains a challenge. In this paper, we propose to model each document as a multivariate Gaussian distribution based on the distributed representations of its words. We then measure the similarity between two documents based on the similarity of their distributions. Experiments on eight standard text categorization datasets demonstrate the effectiveness of the proposed approach in comparison with state-of-the-art methods.
Anthology ID:
E17-2072
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
450–455
Language:
URL:
https://aclanthology.org/E17-2072
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/E17-2072.pdf