@inproceedings{rezaee-ferraro-2023-revup,
title = "{R}ev{U}p: Revise and Update Information Bottleneck for Event Representation",
author = "Rezaee, Mehdi and
Ferraro, Francis",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.56",
doi = "10.18653/v1/2023.eacl-main.56",
pages = "797--814",
abstract = "The existence of external ({``}side{''}) semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information bottleneck-based discrete latent variable model. We reparameterize the model{'}s discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. Our model is learned to minimize the mutual information between the observed data and optional side knowledge that is not already captured by the new, auxiliary variables. We theoretically show that our approach generalizes past approaches, and perform an empirical case study of our approach on event modeling. We corroborate our theoretical results with strong empirical experiments, showing that the proposed method outperforms previous proposed approaches on multiple datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rezaee-ferraro-2023-revup">
<titleInfo>
<title>RevUp: Revise and Update Information Bottleneck for Event Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mehdi</namePart>
<namePart type="family">Rezaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Ferraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The existence of external (“side”) semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information bottleneck-based discrete latent variable model. We reparameterize the model’s discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. Our model is learned to minimize the mutual information between the observed data and optional side knowledge that is not already captured by the new, auxiliary variables. We theoretically show that our approach generalizes past approaches, and perform an empirical case study of our approach on event modeling. We corroborate our theoretical results with strong empirical experiments, showing that the proposed method outperforms previous proposed approaches on multiple datasets.</abstract>
<identifier type="citekey">rezaee-ferraro-2023-revup</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.56</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.56</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>797</start>
<end>814</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RevUp: Revise and Update Information Bottleneck for Event Representation
%A Rezaee, Mehdi
%A Ferraro, Francis
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F rezaee-ferraro-2023-revup
%X The existence of external (“side”) semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information bottleneck-based discrete latent variable model. We reparameterize the model’s discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure. Our model is learned to minimize the mutual information between the observed data and optional side knowledge that is not already captured by the new, auxiliary variables. We theoretically show that our approach generalizes past approaches, and perform an empirical case study of our approach on event modeling. We corroborate our theoretical results with strong empirical experiments, showing that the proposed method outperforms previous proposed approaches on multiple datasets.
%R 10.18653/v1/2023.eacl-main.56
%U https://aclanthology.org/2023.eacl-main.56
%U https://doi.org/10.18653/v1/2023.eacl-main.56
%P 797-814
Markdown (Informal)
[RevUp: Revise and Update Information Bottleneck for Event Representation](https://aclanthology.org/2023.eacl-main.56) (Rezaee & Ferraro, EACL 2023)
ACL