@inproceedings{gaonkar-etal-2020-modeling,
title = "Modeling Label Semantics for Predicting Emotional Reactions",
author = "Gaonkar, Radhika and
Kwon, Heeyoung and
Bastan, Mohaddeseh and
Balasubramanian, Niranjan and
Chambers, Nathanael",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.426/",
doi = "10.18653/v1/2020.acl-main.426",
pages = "4687--4692",
abstract = "Predicting how events induce emotions in the characters of a story is typically seen as a standard multi-label classification task, which usually treats labels as anonymous classes to predict. They ignore information that may be conveyed by the emotion labels themselves. We propose that the semantics of emotion labels can guide a model`s attention when representing the input story. Further, we observe that the emotions evoked by an event are often related: an event that evokes joy is unlikely to also evoke sadness. In this work, we explicitly model label classes via label embeddings, and add mechanisms that track label-label correlations both during training and inference. We also introduce a new semi-supervision strategy that regularizes for the correlations on unlabeled data. Our empirical evaluations show that modeling label semantics yields consistent benefits, and we advance the state-of-the-art on an emotion inference task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaonkar-etal-2020-modeling">
<titleInfo>
<title>Modeling Label Semantics for Predicting Emotional Reactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Radhika</namePart>
<namePart type="family">Gaonkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heeyoung</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohaddeseh</namePart>
<namePart type="family">Bastan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niranjan</namePart>
<namePart type="family">Balasubramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathanael</namePart>
<namePart type="family">Chambers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Predicting how events induce emotions in the characters of a story is typically seen as a standard multi-label classification task, which usually treats labels as anonymous classes to predict. They ignore information that may be conveyed by the emotion labels themselves. We propose that the semantics of emotion labels can guide a model‘s attention when representing the input story. Further, we observe that the emotions evoked by an event are often related: an event that evokes joy is unlikely to also evoke sadness. In this work, we explicitly model label classes via label embeddings, and add mechanisms that track label-label correlations both during training and inference. We also introduce a new semi-supervision strategy that regularizes for the correlations on unlabeled data. Our empirical evaluations show that modeling label semantics yields consistent benefits, and we advance the state-of-the-art on an emotion inference task.</abstract>
<identifier type="citekey">gaonkar-etal-2020-modeling</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.426</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.426/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>4687</start>
<end>4692</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Label Semantics for Predicting Emotional Reactions
%A Gaonkar, Radhika
%A Kwon, Heeyoung
%A Bastan, Mohaddeseh
%A Balasubramanian, Niranjan
%A Chambers, Nathanael
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F gaonkar-etal-2020-modeling
%X Predicting how events induce emotions in the characters of a story is typically seen as a standard multi-label classification task, which usually treats labels as anonymous classes to predict. They ignore information that may be conveyed by the emotion labels themselves. We propose that the semantics of emotion labels can guide a model‘s attention when representing the input story. Further, we observe that the emotions evoked by an event are often related: an event that evokes joy is unlikely to also evoke sadness. In this work, we explicitly model label classes via label embeddings, and add mechanisms that track label-label correlations both during training and inference. We also introduce a new semi-supervision strategy that regularizes for the correlations on unlabeled data. Our empirical evaluations show that modeling label semantics yields consistent benefits, and we advance the state-of-the-art on an emotion inference task.
%R 10.18653/v1/2020.acl-main.426
%U https://aclanthology.org/2020.acl-main.426/
%U https://doi.org/10.18653/v1/2020.acl-main.426
%P 4687-4692
Markdown (Informal)
[Modeling Label Semantics for Predicting Emotional Reactions](https://aclanthology.org/2020.acl-main.426/) (Gaonkar et al., ACL 2020)
ACL
- Radhika Gaonkar, Heeyoung Kwon, Mohaddeseh Bastan, Niranjan Balasubramanian, and Nathanael Chambers. 2020. Modeling Label Semantics for Predicting Emotional Reactions. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4687–4692, Online. Association for Computational Linguistics.