@inproceedings{zhang-etal-2021-unsupervised,
title = "Unsupervised Concept Representation Learning for Length-Varying Text Similarity",
author = "Zhang, Xuchao and
Zong, Bo and
Cheng, Wei and
Ni, Jingchao and
Liu, Yanchi and
Chen, Haifeng",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.445",
doi = "10.18653/v1/2021.naacl-main.445",
pages = "5611--5620",
abstract = "Measuring document similarity plays an important role in natural language processing tasks. Most existing document similarity approaches suffer from the information gap caused by context and vocabulary mismatches when comparing varying-length texts. In this paper, we propose an unsupervised concept representation learning approach to address the above issues. Specifically, we propose a novel Concept Generation Network (CGNet) to learn concept representations from the perspective of the entire text corpus. Moreover, a concept-based document matching method is proposed to leverage advances in the recognition of local phrase features and corpus-level concept features. Extensive experiments on real-world data sets demonstrate that new method can achieve a considerable improvement in comparing length-varying texts. In particular, our model achieved 6.5{\%} better F1 Score compared to the best of the baseline models for a concept-project benchmark dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2021-unsupervised">
<titleInfo>
<title>Unsupervised Concept Representation Learning for Length-Varying Text Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuchao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingchao</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanchi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Measuring document similarity plays an important role in natural language processing tasks. Most existing document similarity approaches suffer from the information gap caused by context and vocabulary mismatches when comparing varying-length texts. In this paper, we propose an unsupervised concept representation learning approach to address the above issues. Specifically, we propose a novel Concept Generation Network (CGNet) to learn concept representations from the perspective of the entire text corpus. Moreover, a concept-based document matching method is proposed to leverage advances in the recognition of local phrase features and corpus-level concept features. Extensive experiments on real-world data sets demonstrate that new method can achieve a considerable improvement in comparing length-varying texts. In particular, our model achieved 6.5% better F1 Score compared to the best of the baseline models for a concept-project benchmark dataset.</abstract>
<identifier type="citekey">zhang-etal-2021-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.445</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.445</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5611</start>
<end>5620</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Concept Representation Learning for Length-Varying Text Similarity
%A Zhang, Xuchao
%A Zong, Bo
%A Cheng, Wei
%A Ni, Jingchao
%A Liu, Yanchi
%A Chen, Haifeng
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F zhang-etal-2021-unsupervised
%X Measuring document similarity plays an important role in natural language processing tasks. Most existing document similarity approaches suffer from the information gap caused by context and vocabulary mismatches when comparing varying-length texts. In this paper, we propose an unsupervised concept representation learning approach to address the above issues. Specifically, we propose a novel Concept Generation Network (CGNet) to learn concept representations from the perspective of the entire text corpus. Moreover, a concept-based document matching method is proposed to leverage advances in the recognition of local phrase features and corpus-level concept features. Extensive experiments on real-world data sets demonstrate that new method can achieve a considerable improvement in comparing length-varying texts. In particular, our model achieved 6.5% better F1 Score compared to the best of the baseline models for a concept-project benchmark dataset.
%R 10.18653/v1/2021.naacl-main.445
%U https://aclanthology.org/2021.naacl-main.445
%U https://doi.org/10.18653/v1/2021.naacl-main.445
%P 5611-5620
Markdown (Informal)
[Unsupervised Concept Representation Learning for Length-Varying Text Similarity](https://aclanthology.org/2021.naacl-main.445) (Zhang et al., NAACL 2021)
ACL