@inproceedings{hao-paul-2019-analyzing,
title = "Analyzing {B}ayesian Crosslingual Transfer in Topic Models",
author = "Hao, Shudong and
Paul, Michael J.",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1158",
doi = "10.18653/v1/N19-1158",
pages = "1551--1565",
abstract = "We introduce a theoretical analysis of crosslingual transfer in probabilistic topic models. By formulating posterior inference through Gibbs sampling as a process of language transfer, we propose a new measure that quantifies the loss of knowledge across languages during this process. This measure enables us to derive a PAC-Bayesian bound that elucidates the factors affecting model quality, both during training and in downstream applications. We provide experimental validation of the analysis on a diverse set of five languages, and discuss best practices for data collection and model design based on our analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hao-paul-2019-analyzing">
<titleInfo>
<title>Analyzing Bayesian Crosslingual Transfer in Topic Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shudong</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a theoretical analysis of crosslingual transfer in probabilistic topic models. By formulating posterior inference through Gibbs sampling as a process of language transfer, we propose a new measure that quantifies the loss of knowledge across languages during this process. This measure enables us to derive a PAC-Bayesian bound that elucidates the factors affecting model quality, both during training and in downstream applications. We provide experimental validation of the analysis on a diverse set of five languages, and discuss best practices for data collection and model design based on our analysis.</abstract>
<identifier type="citekey">hao-paul-2019-analyzing</identifier>
<identifier type="doi">10.18653/v1/N19-1158</identifier>
<location>
<url>https://aclanthology.org/N19-1158</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1551</start>
<end>1565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing Bayesian Crosslingual Transfer in Topic Models
%A Hao, Shudong
%A Paul, Michael J.
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F hao-paul-2019-analyzing
%X We introduce a theoretical analysis of crosslingual transfer in probabilistic topic models. By formulating posterior inference through Gibbs sampling as a process of language transfer, we propose a new measure that quantifies the loss of knowledge across languages during this process. This measure enables us to derive a PAC-Bayesian bound that elucidates the factors affecting model quality, both during training and in downstream applications. We provide experimental validation of the analysis on a diverse set of five languages, and discuss best practices for data collection and model design based on our analysis.
%R 10.18653/v1/N19-1158
%U https://aclanthology.org/N19-1158
%U https://doi.org/10.18653/v1/N19-1158
%P 1551-1565
Markdown (Informal)
[Analyzing Bayesian Crosslingual Transfer in Topic Models](https://aclanthology.org/N19-1158) (Hao & Paul, NAACL 2019)
ACL
- Shudong Hao and Michael J. Paul. 2019. Analyzing Bayesian Crosslingual Transfer in Topic Models. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1551–1565, Minneapolis, Minnesota. Association for Computational Linguistics.