@inproceedings{tay-etal-2021-measuring,
title = "Measuring Similarity of Opinion-bearing Sentences",
author = "Tay, Wenyi and
Zhang, Xiuzhen and
Wan, Stephen and
Karimi, Sarvnaz",
editor = "Carenini, Giuseppe and
Cheung, Jackie Chi Kit and
Dong, Yue and
Liu, Fei and
Wang, Lu",
booktitle = "Proceedings of the Third Workshop on New Frontiers in Summarization",
month = nov,
year = "2021",
address = "Online and in Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.newsum-1.9",
doi = "10.18653/v1/2021.newsum-1.9",
pages = "74--84",
abstract = "For many NLP applications of online reviews, comparison of two opinion-bearing sentences is key. We argue that, while general purpose text similarity metrics have been applied for this purpose, there has been limited exploration of their applicability to opinion texts. We address this gap in the literature, studying: (1) how humans judge the similarity of pairs of opinion-bearing sentences; and, (2) the degree to which existing text similarity metrics, particularly embedding-based ones, correspond to human judgments. We crowdsourced annotations for opinion sentence pairs and our main findings are: (1) annotators tend to agree on whether or not opinion sentences are similar or different; and (2) embedding-based metrics capture human judgments of {``}opinion similarity{''} but not {``}opinion difference{''}. Based on our analysis, we identify areas where the current metrics should be improved. We further propose to learn a similarity metric for opinion similarity via fine-tuning the Sentence-BERT sentence-embedding network based on review text and weak supervision by review ratings. Experiments show that our learned metric outperforms existing text similarity metrics and especially show significantly higher correlations with human annotations for differing opinions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tay-etal-2021-measuring">
<titleInfo>
<title>Measuring Similarity of Opinion-bearing Sentences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenyi</namePart>
<namePart type="family">Tay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuzhen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarvnaz</namePart>
<namePart type="family">Karimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on New Frontiers in Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Carenini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackie</namePart>
<namePart type="given">Chi</namePart>
<namePart type="given">Kit</namePart>
<namePart type="family">Cheung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and in Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For many NLP applications of online reviews, comparison of two opinion-bearing sentences is key. We argue that, while general purpose text similarity metrics have been applied for this purpose, there has been limited exploration of their applicability to opinion texts. We address this gap in the literature, studying: (1) how humans judge the similarity of pairs of opinion-bearing sentences; and, (2) the degree to which existing text similarity metrics, particularly embedding-based ones, correspond to human judgments. We crowdsourced annotations for opinion sentence pairs and our main findings are: (1) annotators tend to agree on whether or not opinion sentences are similar or different; and (2) embedding-based metrics capture human judgments of “opinion similarity” but not “opinion difference”. Based on our analysis, we identify areas where the current metrics should be improved. We further propose to learn a similarity metric for opinion similarity via fine-tuning the Sentence-BERT sentence-embedding network based on review text and weak supervision by review ratings. Experiments show that our learned metric outperforms existing text similarity metrics and especially show significantly higher correlations with human annotations for differing opinions.</abstract>
<identifier type="citekey">tay-etal-2021-measuring</identifier>
<identifier type="doi">10.18653/v1/2021.newsum-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.newsum-1.9</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>74</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Similarity of Opinion-bearing Sentences
%A Tay, Wenyi
%A Zhang, Xiuzhen
%A Wan, Stephen
%A Karimi, Sarvnaz
%Y Carenini, Giuseppe
%Y Cheung, Jackie Chi Kit
%Y Dong, Yue
%Y Liu, Fei
%Y Wang, Lu
%S Proceedings of the Third Workshop on New Frontiers in Summarization
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and in Dominican Republic
%F tay-etal-2021-measuring
%X For many NLP applications of online reviews, comparison of two opinion-bearing sentences is key. We argue that, while general purpose text similarity metrics have been applied for this purpose, there has been limited exploration of their applicability to opinion texts. We address this gap in the literature, studying: (1) how humans judge the similarity of pairs of opinion-bearing sentences; and, (2) the degree to which existing text similarity metrics, particularly embedding-based ones, correspond to human judgments. We crowdsourced annotations for opinion sentence pairs and our main findings are: (1) annotators tend to agree on whether or not opinion sentences are similar or different; and (2) embedding-based metrics capture human judgments of “opinion similarity” but not “opinion difference”. Based on our analysis, we identify areas where the current metrics should be improved. We further propose to learn a similarity metric for opinion similarity via fine-tuning the Sentence-BERT sentence-embedding network based on review text and weak supervision by review ratings. Experiments show that our learned metric outperforms existing text similarity metrics and especially show significantly higher correlations with human annotations for differing opinions.
%R 10.18653/v1/2021.newsum-1.9
%U https://aclanthology.org/2021.newsum-1.9
%U https://doi.org/10.18653/v1/2021.newsum-1.9
%P 74-84
Markdown (Informal)
[Measuring Similarity of Opinion-bearing Sentences](https://aclanthology.org/2021.newsum-1.9) (Tay et al., NewSum 2021)
ACL
- Wenyi Tay, Xiuzhen Zhang, Stephen Wan, and Sarvnaz Karimi. 2021. Measuring Similarity of Opinion-bearing Sentences. In Proceedings of the Third Workshop on New Frontiers in Summarization, pages 74–84, Online and in Dominican Republic. Association for Computational Linguistics.