@inproceedings{saadany-etal-2021-sentiment,
title = "Sentiment-Aware Measure ({SAM}) for Evaluating Sentiment Transfer by Machine Translation Systems",
author = "Saadany, Hadeel and
Or{\u{a}}san, Constantin and
Mohamed, Emad and
Tantavy, Ashraf",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.137",
pages = "1217--1226",
abstract = "In translating text where sentiment is the main message, human translators give particular attention to sentiment-carrying words. The reason is that an incorrect translation of such words would miss the fundamental aspect of the source text, i.e. the author{'}s sentiment. In the online world, MT systems are extensively used to translate User-Generated Content (UGC) such as reviews, tweets, and social media posts, where the main message is often the author{'}s positive or negative attitude towards the topic of the text. It is important in such scenarios to accurately measure how far an MT system can be a reliable real-life utility in transferring the correct affect message. This paper tackles an under-recognized problem in the field of machine translation evaluation which is judging to what extent automatic metrics concur with the gold standard of human evaluation for a correct translation of sentiment. We evaluate the efficacy of conventional quality metrics in spotting a mistranslation of sentiment, especially when it is the sole error in the MT output. We propose a numerical {``}sentiment-closeness{''} measure appropriate for assessing the accuracy of a translated affect message in UGC text by an MT system. We will show that incorporating this sentiment-aware measure can significantly enhance the correlation of some available quality metrics with the human judgement of an accurate translation of sentiment.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saadany-etal-2021-sentiment">
<titleInfo>
<title>Sentiment-Aware Measure (SAM) for Evaluating Sentiment Transfer by Machine Translation Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hadeel</namePart>
<namePart type="family">Saadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantin</namePart>
<namePart type="family">Orăsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emad</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashraf</namePart>
<namePart type="family">Tantavy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In translating text where sentiment is the main message, human translators give particular attention to sentiment-carrying words. The reason is that an incorrect translation of such words would miss the fundamental aspect of the source text, i.e. the author’s sentiment. In the online world, MT systems are extensively used to translate User-Generated Content (UGC) such as reviews, tweets, and social media posts, where the main message is often the author’s positive or negative attitude towards the topic of the text. It is important in such scenarios to accurately measure how far an MT system can be a reliable real-life utility in transferring the correct affect message. This paper tackles an under-recognized problem in the field of machine translation evaluation which is judging to what extent automatic metrics concur with the gold standard of human evaluation for a correct translation of sentiment. We evaluate the efficacy of conventional quality metrics in spotting a mistranslation of sentiment, especially when it is the sole error in the MT output. We propose a numerical “sentiment-closeness” measure appropriate for assessing the accuracy of a translated affect message in UGC text by an MT system. We will show that incorporating this sentiment-aware measure can significantly enhance the correlation of some available quality metrics with the human judgement of an accurate translation of sentiment.</abstract>
<identifier type="citekey">saadany-etal-2021-sentiment</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.137</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>1217</start>
<end>1226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment-Aware Measure (SAM) for Evaluating Sentiment Transfer by Machine Translation Systems
%A Saadany, Hadeel
%A Orăsan, Constantin
%A Mohamed, Emad
%A Tantavy, Ashraf
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F saadany-etal-2021-sentiment
%X In translating text where sentiment is the main message, human translators give particular attention to sentiment-carrying words. The reason is that an incorrect translation of such words would miss the fundamental aspect of the source text, i.e. the author’s sentiment. In the online world, MT systems are extensively used to translate User-Generated Content (UGC) such as reviews, tweets, and social media posts, where the main message is often the author’s positive or negative attitude towards the topic of the text. It is important in such scenarios to accurately measure how far an MT system can be a reliable real-life utility in transferring the correct affect message. This paper tackles an under-recognized problem in the field of machine translation evaluation which is judging to what extent automatic metrics concur with the gold standard of human evaluation for a correct translation of sentiment. We evaluate the efficacy of conventional quality metrics in spotting a mistranslation of sentiment, especially when it is the sole error in the MT output. We propose a numerical “sentiment-closeness” measure appropriate for assessing the accuracy of a translated affect message in UGC text by an MT system. We will show that incorporating this sentiment-aware measure can significantly enhance the correlation of some available quality metrics with the human judgement of an accurate translation of sentiment.
%U https://aclanthology.org/2021.ranlp-1.137
%P 1217-1226
Markdown (Informal)
[Sentiment-Aware Measure (SAM) for Evaluating Sentiment Transfer by Machine Translation Systems](https://aclanthology.org/2021.ranlp-1.137) (Saadany et al., RANLP 2021)
ACL