@inproceedings{huang-etal-2022-distilling,
title = "Distilling Salient Reviews with Zero Labels",
author = "Huang, Chieh-Yang and
Li, Jinfeng and
Bhutani, Nikita and
Whedon, Alexander and
Hruschka, Estevam and
Suhara, Yoshi",
editor = "Aly, Rami and
Christodoulopoulos, Christos and
Cocarascu, Oana and
Guo, Zhijiang and
Mittal, Arpit and
Schlichtkrull, Michael and
Thorne, James and
Vlachos, Andreas",
booktitle = "Proceedings of the Fifth Fact Extraction and VERification Workshop (FEVER)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.fever-1.3/",
doi = "10.18653/v1/2022.fever-1.3",
pages = "16--28",
abstract = "Many people read online reviews to learn about real-world entities of their interest. However, majority of reviews only describes general experiences and opinions of the customers, and may not reveal facts that are specific to the entity being reviewed. In this work, we focus on a novel task of mining from a review corpus sentences that are unique for each entity. We refer to this task as Salient Fact Extraction. Salient facts are extremely scarce due to their very nature. Consequently, collecting labeled examples for training supervised models is tedious and cost-prohibitive. To alleviate this scarcity problem, we develop an unsupervised method, ZL-Distiller, which leverages contextual language representations of the reviews and their distributional patterns to identify salient sentences about entities. Our experiments on multiple domains (hotels, products, and restaurants) show that ZL-Distiller achieves state-of-the-art performance and further boosts the performance of other supervised/unsupervised algorithms for the task. Furthermore, we show that salient sentences mined by ZL-Distiller provide unique and detailed information about entities, which benefit downstream NLP applications including question answering and summarization."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-distilling">
<titleInfo>
<title>Distilling Salient Reviews with Zero Labels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chieh-Yang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinfeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Bhutani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Whedon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Estevam</namePart>
<namePart type="family">Hruschka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshi</namePart>
<namePart type="family">Suhara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Fact Extraction and VERification Workshop (FEVER)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rami</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Cocarascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijiang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpit</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Schlichtkrull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Thorne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many people read online reviews to learn about real-world entities of their interest. However, majority of reviews only describes general experiences and opinions of the customers, and may not reveal facts that are specific to the entity being reviewed. In this work, we focus on a novel task of mining from a review corpus sentences that are unique for each entity. We refer to this task as Salient Fact Extraction. Salient facts are extremely scarce due to their very nature. Consequently, collecting labeled examples for training supervised models is tedious and cost-prohibitive. To alleviate this scarcity problem, we develop an unsupervised method, ZL-Distiller, which leverages contextual language representations of the reviews and their distributional patterns to identify salient sentences about entities. Our experiments on multiple domains (hotels, products, and restaurants) show that ZL-Distiller achieves state-of-the-art performance and further boosts the performance of other supervised/unsupervised algorithms for the task. Furthermore, we show that salient sentences mined by ZL-Distiller provide unique and detailed information about entities, which benefit downstream NLP applications including question answering and summarization.</abstract>
<identifier type="citekey">huang-etal-2022-distilling</identifier>
<identifier type="doi">10.18653/v1/2022.fever-1.3</identifier>
<location>
<url>https://aclanthology.org/2022.fever-1.3/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>16</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Distilling Salient Reviews with Zero Labels
%A Huang, Chieh-Yang
%A Li, Jinfeng
%A Bhutani, Nikita
%A Whedon, Alexander
%A Hruschka, Estevam
%A Suhara, Yoshi
%Y Aly, Rami
%Y Christodoulopoulos, Christos
%Y Cocarascu, Oana
%Y Guo, Zhijiang
%Y Mittal, Arpit
%Y Schlichtkrull, Michael
%Y Thorne, James
%Y Vlachos, Andreas
%S Proceedings of the Fifth Fact Extraction and VERification Workshop (FEVER)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F huang-etal-2022-distilling
%X Many people read online reviews to learn about real-world entities of their interest. However, majority of reviews only describes general experiences and opinions of the customers, and may not reveal facts that are specific to the entity being reviewed. In this work, we focus on a novel task of mining from a review corpus sentences that are unique for each entity. We refer to this task as Salient Fact Extraction. Salient facts are extremely scarce due to their very nature. Consequently, collecting labeled examples for training supervised models is tedious and cost-prohibitive. To alleviate this scarcity problem, we develop an unsupervised method, ZL-Distiller, which leverages contextual language representations of the reviews and their distributional patterns to identify salient sentences about entities. Our experiments on multiple domains (hotels, products, and restaurants) show that ZL-Distiller achieves state-of-the-art performance and further boosts the performance of other supervised/unsupervised algorithms for the task. Furthermore, we show that salient sentences mined by ZL-Distiller provide unique and detailed information about entities, which benefit downstream NLP applications including question answering and summarization.
%R 10.18653/v1/2022.fever-1.3
%U https://aclanthology.org/2022.fever-1.3/
%U https://doi.org/10.18653/v1/2022.fever-1.3
%P 16-28
Markdown (Informal)
[Distilling Salient Reviews with Zero Labels](https://aclanthology.org/2022.fever-1.3/) (Huang et al., FEVER 2022)
ACL
- Chieh-Yang Huang, Jinfeng Li, Nikita Bhutani, Alexander Whedon, Estevam Hruschka, and Yoshi Suhara. 2022. Distilling Salient Reviews with Zero Labels. In Proceedings of the Fifth Fact Extraction and VERification Workshop (FEVER), pages 16–28, Dublin, Ireland. Association for Computational Linguistics.