@inproceedings{dou-etal-2021-cvae-based,
title = "{CVAE}-based Re-anchoring for Implicit Discourse Relation Classification",
author = "Dou, Zujun and
Hong, Yu and
Sun, Yu and
Zhou, Guodong",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.110",
doi = "10.18653/v1/2021.findings-emnlp.110",
pages = "1275--1283",
abstract = "Training implicit discourse relation classifiers suffers from data sparsity. Variational AutoEncoder (VAE) appears to be the proper solution. It is because ideally VAE is capable of generating inexhaustible varying samples, and this facilitates selective data augmentation. However, our experiments show that coupling VAE with the RoBERTa-based classifier results in severe performance degradation. We ascribe the unusual phenomenon to erroneous sampling that would happen when VAE pursued variations. To overcome the problem, we develop a re-anchoring strategy, where Conditional VAE (CVAE) is used for estimating the risk of erroneous sampling, and meanwhile migrating the anchor to reduce the risk. The test results on PDTB v2.0 illustrate that, compared to the RoBERTa-based baseline, re-anchoring yields substantial improvements. Besides, we observe that re-anchoring can cooperate with other auxiliary strategies (transfer learning and interactive attention mechanism) to further improve the baseline, obtaining the F-scores of about 55{\%}, 63{\%}, 80{\%} and 44{\%} for the four main relation types (Comparison, Contingency, Expansion, Temporality) in the binary classification (Yes/No) scenario.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dou-etal-2021-cvae-based">
<titleInfo>
<title>CVAE-based Re-anchoring for Implicit Discourse Relation Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zujun</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guodong</namePart>
<namePart type="family">Zhou</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>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Training implicit discourse relation classifiers suffers from data sparsity. Variational AutoEncoder (VAE) appears to be the proper solution. It is because ideally VAE is capable of generating inexhaustible varying samples, and this facilitates selective data augmentation. However, our experiments show that coupling VAE with the RoBERTa-based classifier results in severe performance degradation. We ascribe the unusual phenomenon to erroneous sampling that would happen when VAE pursued variations. To overcome the problem, we develop a re-anchoring strategy, where Conditional VAE (CVAE) is used for estimating the risk of erroneous sampling, and meanwhile migrating the anchor to reduce the risk. The test results on PDTB v2.0 illustrate that, compared to the RoBERTa-based baseline, re-anchoring yields substantial improvements. Besides, we observe that re-anchoring can cooperate with other auxiliary strategies (transfer learning and interactive attention mechanism) to further improve the baseline, obtaining the F-scores of about 55%, 63%, 80% and 44% for the four main relation types (Comparison, Contingency, Expansion, Temporality) in the binary classification (Yes/No) scenario.</abstract>
<identifier type="citekey">dou-etal-2021-cvae-based</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.110</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.110</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1275</start>
<end>1283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CVAE-based Re-anchoring for Implicit Discourse Relation Classification
%A Dou, Zujun
%A Hong, Yu
%A Sun, Yu
%A Zhou, Guodong
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F dou-etal-2021-cvae-based
%X Training implicit discourse relation classifiers suffers from data sparsity. Variational AutoEncoder (VAE) appears to be the proper solution. It is because ideally VAE is capable of generating inexhaustible varying samples, and this facilitates selective data augmentation. However, our experiments show that coupling VAE with the RoBERTa-based classifier results in severe performance degradation. We ascribe the unusual phenomenon to erroneous sampling that would happen when VAE pursued variations. To overcome the problem, we develop a re-anchoring strategy, where Conditional VAE (CVAE) is used for estimating the risk of erroneous sampling, and meanwhile migrating the anchor to reduce the risk. The test results on PDTB v2.0 illustrate that, compared to the RoBERTa-based baseline, re-anchoring yields substantial improvements. Besides, we observe that re-anchoring can cooperate with other auxiliary strategies (transfer learning and interactive attention mechanism) to further improve the baseline, obtaining the F-scores of about 55%, 63%, 80% and 44% for the four main relation types (Comparison, Contingency, Expansion, Temporality) in the binary classification (Yes/No) scenario.
%R 10.18653/v1/2021.findings-emnlp.110
%U https://aclanthology.org/2021.findings-emnlp.110
%U https://doi.org/10.18653/v1/2021.findings-emnlp.110
%P 1275-1283
Markdown (Informal)
[CVAE-based Re-anchoring for Implicit Discourse Relation Classification](https://aclanthology.org/2021.findings-emnlp.110) (Dou et al., Findings 2021)
ACL