@inproceedings{zhang-etal-2022-curriculum,
title = "Curriculum Knowledge Distillation for Emoji-supervised Cross-lingual Sentiment Analysis",
author = "Zhang, Jianyang and
Liang, Tao and
Wan, Mingyang and
Yang, Guowu and
Lv, Fengmao",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.55",
doi = "10.18653/v1/2022.emnlp-main.55",
pages = "864--875",
abstract = "Existing sentiment analysis models have achieved great advances with the help of sufficient sentiment annotations. Unfortunately, many languages do not have sufficient sentiment corpus. To this end, recent studies have proposed cross-lingual sentiment analysis to transfer sentiment analysis models from resource-rich languages to low-resource languages. However, these studies either rely on external cross-lingual supervision (e.g., parallel corpora and translation model), or are limited by the cross-lingual gaps. In this work, based on the intuitive assumption that the relationships between emojis and sentiments are consistent across different languages, we investigate transferring sentiment knowledge across languages with the help of emojis. To this end, we propose a novel cross-lingual sentiment analysis approach dubbed Curriculum Knowledge Distiller (CKD). The core idea of CKD is to use emojis to bridge the source and target languages. Note that, compared with texts, emojis are more transferable, but cannot reveal the precise sentiment. Thus, we distill multiple Intermediate Sentiment Classifiers (ISC) on source language corpus with emojis to get ISCs with different attention weights of texts. To transfer them into the target language, we distill ISCs into the Target Language Sentiment Classifier (TSC) following the curriculum learning mechanism. In this way, TSC can learn delicate sentiment knowledge, meanwhile, avoid being affected by cross-lingual gaps. Experimental results on five cross-lingual benchmarks clearly verify the effectiveness of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-curriculum">
<titleInfo>
<title>Curriculum Knowledge Distillation for Emoji-supervised Cross-lingual Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guowu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengmao</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing sentiment analysis models have achieved great advances with the help of sufficient sentiment annotations. Unfortunately, many languages do not have sufficient sentiment corpus. To this end, recent studies have proposed cross-lingual sentiment analysis to transfer sentiment analysis models from resource-rich languages to low-resource languages. However, these studies either rely on external cross-lingual supervision (e.g., parallel corpora and translation model), or are limited by the cross-lingual gaps. In this work, based on the intuitive assumption that the relationships between emojis and sentiments are consistent across different languages, we investigate transferring sentiment knowledge across languages with the help of emojis. To this end, we propose a novel cross-lingual sentiment analysis approach dubbed Curriculum Knowledge Distiller (CKD). The core idea of CKD is to use emojis to bridge the source and target languages. Note that, compared with texts, emojis are more transferable, but cannot reveal the precise sentiment. Thus, we distill multiple Intermediate Sentiment Classifiers (ISC) on source language corpus with emojis to get ISCs with different attention weights of texts. To transfer them into the target language, we distill ISCs into the Target Language Sentiment Classifier (TSC) following the curriculum learning mechanism. In this way, TSC can learn delicate sentiment knowledge, meanwhile, avoid being affected by cross-lingual gaps. Experimental results on five cross-lingual benchmarks clearly verify the effectiveness of our approach.</abstract>
<identifier type="citekey">zhang-etal-2022-curriculum</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.55</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.55</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>864</start>
<end>875</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Curriculum Knowledge Distillation for Emoji-supervised Cross-lingual Sentiment Analysis
%A Zhang, Jianyang
%A Liang, Tao
%A Wan, Mingyang
%A Yang, Guowu
%A Lv, Fengmao
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhang-etal-2022-curriculum
%X Existing sentiment analysis models have achieved great advances with the help of sufficient sentiment annotations. Unfortunately, many languages do not have sufficient sentiment corpus. To this end, recent studies have proposed cross-lingual sentiment analysis to transfer sentiment analysis models from resource-rich languages to low-resource languages. However, these studies either rely on external cross-lingual supervision (e.g., parallel corpora and translation model), or are limited by the cross-lingual gaps. In this work, based on the intuitive assumption that the relationships between emojis and sentiments are consistent across different languages, we investigate transferring sentiment knowledge across languages with the help of emojis. To this end, we propose a novel cross-lingual sentiment analysis approach dubbed Curriculum Knowledge Distiller (CKD). The core idea of CKD is to use emojis to bridge the source and target languages. Note that, compared with texts, emojis are more transferable, but cannot reveal the precise sentiment. Thus, we distill multiple Intermediate Sentiment Classifiers (ISC) on source language corpus with emojis to get ISCs with different attention weights of texts. To transfer them into the target language, we distill ISCs into the Target Language Sentiment Classifier (TSC) following the curriculum learning mechanism. In this way, TSC can learn delicate sentiment knowledge, meanwhile, avoid being affected by cross-lingual gaps. Experimental results on five cross-lingual benchmarks clearly verify the effectiveness of our approach.
%R 10.18653/v1/2022.emnlp-main.55
%U https://aclanthology.org/2022.emnlp-main.55
%U https://doi.org/10.18653/v1/2022.emnlp-main.55
%P 864-875
Markdown (Informal)
[Curriculum Knowledge Distillation for Emoji-supervised Cross-lingual Sentiment Analysis](https://aclanthology.org/2022.emnlp-main.55) (Zhang et al., EMNLP 2022)
ACL