Publication detail

Learning Document Embeddings Along With Their Uncertainties

KESIRAJU, S. PLCHOT, O. BURGET, L. GANGASHETTY, S.

Original Title

Learning Document Embeddings Along With Their Uncertainties

Type

journal article in Web of Science

Language

English

Original Abstract

Majority of the text modeling techniques yield only point-estimates of document embeddings and lack in capturing the uncertainty of the estimates. These uncertainties give a notion of how well the embeddings represent a document. We present Bayesian subspace multinomial model (Bayesian SMM), a generative log-linear model that learns to represent documents in the form of Gaussian distributions, thereby encoding the uncertainty in its covariance. Additionally, in the proposed Bayesian SMM, we address a commonly encountered problem of intractability that appears during variational inference in mixed-logit models. We also present a generative Gaussian linear classifier for topic identification that exploits the uncertainty in document embeddings. Our intrinsic evaluation using perplexity measure shows that the proposed Bayesian SMM fits the unseen test data better as compared to the state-of-the-art neural variational document model on (Fisher) speech and (20Newsgroups) text corpora. Our topic identification experiments showthat the proposed systems are robust to over-fitting on unseen test data. The topic ID results show that the proposedmodel outperforms state-of-the-art unsupervised topic models and achieve comparable results to the state-of-the-art fully supervised discriminative models.

Keywords

Bayesian methods, embeddings, topic identification.

Authors

KESIRAJU, S.; PLCHOT, O.; BURGET, L.; GANGASHETTY, S.

Released

27. 7. 2020

ISBN

2329-9290

Periodical

IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING

Year of study

2020

Number

28

State

United States of America

Pages from

2319

Pages to

2332

Pages count

14

URL

BibTex

@article{BUT168164,
  author="Santosh {Kesiraju} and Oldřich {Plchot} and Lukáš {Burget} and Suryakanth V {Gangashetty}",
  title="Learning Document Embeddings Along With Their Uncertainties",
  journal="IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING",
  year="2020",
  volume="2020",
  number="28",
  pages="2319--2332",
  doi="10.1109/TASLP.2020.3012062",
  issn="2329-9290",
  url="https://ieeexplore.ieee.org/document/9149686"
}