@inproceedings{yu-etal-2020-wasserstein,
title = "{W}asserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains",
author = "Yu, Weijie and
Xu, Chen and
Xu, Jun and
Pang, Liang and
Gao, Xiaopeng and
Wang, Xiaozhao and
Wen, Ji-Rong",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.239",
doi = "10.18653/v1/2020.emnlp-main.239",
pages = "2985--2994",
abstract = "One approach to matching texts from asymmetrical domains is projecting the input sequences into a common semantic space as feature vectors upon which the matching function can be readily defined and learned. In real-world matching practices, it is often observed that with the training goes on, the feature vectors projected from different domains tend to be indistinguishable. The phenomenon, however, is often overlooked in existing matching models. As a result, the feature vectors are constructed without any regularization, which inevitably increases the difficulty of learning the downstream matching functions. In this paper, we propose a novel match method tailored for text matching in asymmetrical domains, called WD-Match. In WD-Match, a Wasserstein distance-based regularizer is defined to regularize the features vectors projected from different domains. As a result, the method enforces the feature projection function to generate vectors such that those correspond to different domains cannot be easily discriminated. The training process of WD-Match amounts to a game that minimizes the matching loss regularized by the Wasserstein distance. WD-Match can be used to improve different text matching methods, by using the method as its underlying matching model. Four popular text matching methods have been exploited in the paper. Experimental results based on four publicly available benchmarks showed that WD-Match consistently outperformed the underlying methods and the baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2020-wasserstein">
<titleInfo>
<title>Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weijie</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaopeng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaozhao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-Rong</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>One approach to matching texts from asymmetrical domains is projecting the input sequences into a common semantic space as feature vectors upon which the matching function can be readily defined and learned. In real-world matching practices, it is often observed that with the training goes on, the feature vectors projected from different domains tend to be indistinguishable. The phenomenon, however, is often overlooked in existing matching models. As a result, the feature vectors are constructed without any regularization, which inevitably increases the difficulty of learning the downstream matching functions. In this paper, we propose a novel match method tailored for text matching in asymmetrical domains, called WD-Match. In WD-Match, a Wasserstein distance-based regularizer is defined to regularize the features vectors projected from different domains. As a result, the method enforces the feature projection function to generate vectors such that those correspond to different domains cannot be easily discriminated. The training process of WD-Match amounts to a game that minimizes the matching loss regularized by the Wasserstein distance. WD-Match can be used to improve different text matching methods, by using the method as its underlying matching model. Four popular text matching methods have been exploited in the paper. Experimental results based on four publicly available benchmarks showed that WD-Match consistently outperformed the underlying methods and the baselines.</abstract>
<identifier type="citekey">yu-etal-2020-wasserstein</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.239</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.239</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2985</start>
<end>2994</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains
%A Yu, Weijie
%A Xu, Chen
%A Xu, Jun
%A Pang, Liang
%A Gao, Xiaopeng
%A Wang, Xiaozhao
%A Wen, Ji-Rong
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yu-etal-2020-wasserstein
%X One approach to matching texts from asymmetrical domains is projecting the input sequences into a common semantic space as feature vectors upon which the matching function can be readily defined and learned. In real-world matching practices, it is often observed that with the training goes on, the feature vectors projected from different domains tend to be indistinguishable. The phenomenon, however, is often overlooked in existing matching models. As a result, the feature vectors are constructed without any regularization, which inevitably increases the difficulty of learning the downstream matching functions. In this paper, we propose a novel match method tailored for text matching in asymmetrical domains, called WD-Match. In WD-Match, a Wasserstein distance-based regularizer is defined to regularize the features vectors projected from different domains. As a result, the method enforces the feature projection function to generate vectors such that those correspond to different domains cannot be easily discriminated. The training process of WD-Match amounts to a game that minimizes the matching loss regularized by the Wasserstein distance. WD-Match can be used to improve different text matching methods, by using the method as its underlying matching model. Four popular text matching methods have been exploited in the paper. Experimental results based on four publicly available benchmarks showed that WD-Match consistently outperformed the underlying methods and the baselines.
%R 10.18653/v1/2020.emnlp-main.239
%U https://aclanthology.org/2020.emnlp-main.239
%U https://doi.org/10.18653/v1/2020.emnlp-main.239
%P 2985-2994
Markdown (Informal)
[Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains](https://aclanthology.org/2020.emnlp-main.239) (Yu et al., EMNLP 2020)
ACL