@inproceedings{li-etal-2020-hitrans,
title = "{H}i{T}rans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations",
author = "Li, Jingye and
Ji, Donghong and
Li, Fei and
Zhang, Meishan and
Liu, Yijiang",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.370/",
doi = "10.18653/v1/2020.coling-main.370",
pages = "4190--4200",
abstract = "Emotion detection in conversations (EDC) is to detect the emotion for each utterance in conversations that have multiple speakers. Different from the traditional non-conversational emotion detection, the model for EDC should be context-sensitive (e.g., understanding the whole conversation rather than one utterance) and speaker-sensitive (e.g., understanding which utterance belongs to which speaker). In this paper, we propose a transformer-based context- and speaker-sensitive model for EDC, namely HiTrans, which consists of two hierarchical transformers. We utilize BERT as the low-level transformer to generate local utterance representations, and feed them into another high-level transformer so that utterance representations could be sensitive to the global context of the conversation. Moreover, we exploit an auxiliary task to make our model speaker-sensitive, called pairwise utterance speaker verification (PUSV), which aims to classify whether two utterances belong to the same speaker. We evaluate our model on three benchmark datasets, namely EmoryNLP, MELD and IEMOCAP. Results show that our model outperforms previous state-of-the-art models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-hitrans">
<titleInfo>
<title>HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingye</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghong</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meishan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion detection in conversations (EDC) is to detect the emotion for each utterance in conversations that have multiple speakers. Different from the traditional non-conversational emotion detection, the model for EDC should be context-sensitive (e.g., understanding the whole conversation rather than one utterance) and speaker-sensitive (e.g., understanding which utterance belongs to which speaker). In this paper, we propose a transformer-based context- and speaker-sensitive model for EDC, namely HiTrans, which consists of two hierarchical transformers. We utilize BERT as the low-level transformer to generate local utterance representations, and feed them into another high-level transformer so that utterance representations could be sensitive to the global context of the conversation. Moreover, we exploit an auxiliary task to make our model speaker-sensitive, called pairwise utterance speaker verification (PUSV), which aims to classify whether two utterances belong to the same speaker. We evaluate our model on three benchmark datasets, namely EmoryNLP, MELD and IEMOCAP. Results show that our model outperforms previous state-of-the-art models.</abstract>
<identifier type="citekey">li-etal-2020-hitrans</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.370</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.370/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4190</start>
<end>4200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations
%A Li, Jingye
%A Ji, Donghong
%A Li, Fei
%A Zhang, Meishan
%A Liu, Yijiang
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F li-etal-2020-hitrans
%X Emotion detection in conversations (EDC) is to detect the emotion for each utterance in conversations that have multiple speakers. Different from the traditional non-conversational emotion detection, the model for EDC should be context-sensitive (e.g., understanding the whole conversation rather than one utterance) and speaker-sensitive (e.g., understanding which utterance belongs to which speaker). In this paper, we propose a transformer-based context- and speaker-sensitive model for EDC, namely HiTrans, which consists of two hierarchical transformers. We utilize BERT as the low-level transformer to generate local utterance representations, and feed them into another high-level transformer so that utterance representations could be sensitive to the global context of the conversation. Moreover, we exploit an auxiliary task to make our model speaker-sensitive, called pairwise utterance speaker verification (PUSV), which aims to classify whether two utterances belong to the same speaker. We evaluate our model on three benchmark datasets, namely EmoryNLP, MELD and IEMOCAP. Results show that our model outperforms previous state-of-the-art models.
%R 10.18653/v1/2020.coling-main.370
%U https://aclanthology.org/2020.coling-main.370/
%U https://doi.org/10.18653/v1/2020.coling-main.370
%P 4190-4200
Markdown (Informal)
[HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations](https://aclanthology.org/2020.coling-main.370/) (Li et al., COLING 2020)
ACL