Publication detail

Learning document representations using subspace multinomial model

KESIRAJU, S. BURGET, L. SZŐKE, I. ČERNOCKÝ, J.

Original Title

Learning document representations using subspace multinomial model

Type

conference paper

Language

English

Original Abstract

Subspace multinomial model (SMM) is a log-linear model and can be used for learning low dimensional continuous representation for discrete data. SMMand its variants have been used for speaker verification based on prosodic features and phonotactic language recognition. In this paper, we propose a new variant of SMM that introduces sparsity and call the resulting model as `1 SMM. We show that `1 SMM can be used for learning document representations that are helpful in topic identification or classification and clustering tasks. Our experiments in document classification show that SMM achieves comparable results to models such as latent Dirichlet allocation and sparse topical coding, while having a useful property that the resulting document vectors are Gaussian distributed.

Keywords

Document representation, subspace modelling, topic identification, latent topic discovery

Authors

KESIRAJU, S.; BURGET, L.; SZŐKE, I.; ČERNOCKÝ, J.

Released

8. 9. 2016

Publisher

International Speech Communication Association

Location

San Francisco

ISBN

978-1-5108-3313-5

Book

Proceedings of Interspeech 2016

Pages from

700

Pages to

704

Pages count

5

URL

BibTex

@inproceedings{BUT132598,
  author="Santosh {Kesiraju} and Lukáš {Burget} and Igor {Szőke} and Jan {Černocký}",
  title="Learning document representations using subspace multinomial model",
  booktitle="Proceedings of Interspeech 2016",
  year="2016",
  pages="700--704",
  publisher="International Speech Communication Association",
  address="San Francisco",
  doi="10.21437/Interspeech.2016-1634",
  isbn="978-1-5108-3313-5",
  url="https://www.researchgate.net/publication/307889473_Learning_Document_Representations_Using_Subspace_Multinomial_Model"
}