Learning Document Embeddings Along With Their Uncertainties
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU138655" target="_blank" >RIV/00216305:26230/20:PU138655 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/9149686" target="_blank" >https://ieeexplore.ieee.org/document/9149686</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TASLP.2020.3012062" target="_blank" >10.1109/TASLP.2020.3012062</a>
Alternative languages
Result language
angličtina
Original language name
Learning Document Embeddings Along With Their Uncertainties
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING
ISSN
2329-9290
e-ISSN
2329-9304
Volume of the periodical
2020
Issue of the periodical within the volume
28
Country of publishing house
US - UNITED STATES
Number of pages
14
Pages from-to
2319-2332
UT code for WoS article
000562410300004
EID of the result in the Scopus database
2-s2.0-85090796297