@inproceedings{wang-etal-2023-parallel,
title = "Parallel Corpora Alignment Framework for Multilingual and Robust Automatic Dialogue Evaluation",
author = "Wang, Xinglin and
Shi, Jiayi and
Yuan, Peiwen and
Li, Kan",
editor = "Chen, Yun-Nung and
Crook, Paul and
Galley, Michel and
Ghazarian, Sarik and
Gunasekara, Chulaka and
Gupta, Raghav and
Hedayatnia, Behnam and
Kottur, Satwik and
Moon, Seungwhan and
Zhang, Chen",
booktitle = "Proceedings of The Eleventh Dialog System Technology Challenge",
month = sep,
year = "2023",
address = "Prague, Czech Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.dstc-1.15",
pages = "123--132",
abstract = "Open-domain automatic dialogue evaluation plays an important role in dialogue systems. While recent efforts are being put into making learning-based evaluation metrics correlate better with human evaluation, robust metrics for parallel corpora and multiple domains remain unexplored. Parallel corpora refer to corpora that express the same idea in different ways (e.g., translation, paraphrasing and back-translation). In this paper, we propose Parallel Corpora Alignment Framework (PCAF), which improves the consistency and robustness of model evaluation on parallel corpora. Firstly, parallel corpora are aligned in semantic space through parallel-corpora-aligned contrastive learning. Then, parallel-corpora-aligned distillation on multi-dataset is applied to further improve model{'}s generalization ability across multiple data domains. Our approach ranks second on the final test data of DSTC11 track4 subtask1 ({``}Multilingual Automatic Evaluation Metrics{''}, turn-level) and third on the subtask2 ({``}Robust Automatic Evaluation Metrics{''}, turn-level), which proves the strong generalization ability and robustness of our proposed approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-parallel">
<titleInfo>
<title>Parallel Corpora Alignment Framework for Multilingual and Robust Automatic Dialogue Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinglin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiayi</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiwen</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Eleventh Dialog System Technology Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Crook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michel</namePart>
<namePart type="family">Galley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarik</namePart>
<namePart type="family">Ghazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulaka</namePart>
<namePart type="family">Gunasekara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behnam</namePart>
<namePart type="family">Hedayatnia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satwik</namePart>
<namePart type="family">Kottur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seungwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czech Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open-domain automatic dialogue evaluation plays an important role in dialogue systems. While recent efforts are being put into making learning-based evaluation metrics correlate better with human evaluation, robust metrics for parallel corpora and multiple domains remain unexplored. Parallel corpora refer to corpora that express the same idea in different ways (e.g., translation, paraphrasing and back-translation). In this paper, we propose Parallel Corpora Alignment Framework (PCAF), which improves the consistency and robustness of model evaluation on parallel corpora. Firstly, parallel corpora are aligned in semantic space through parallel-corpora-aligned contrastive learning. Then, parallel-corpora-aligned distillation on multi-dataset is applied to further improve model’s generalization ability across multiple data domains. Our approach ranks second on the final test data of DSTC11 track4 subtask1 (“Multilingual Automatic Evaluation Metrics”, turn-level) and third on the subtask2 (“Robust Automatic Evaluation Metrics”, turn-level), which proves the strong generalization ability and robustness of our proposed approach.</abstract>
<identifier type="citekey">wang-etal-2023-parallel</identifier>
<location>
<url>https://aclanthology.org/2023.dstc-1.15</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>123</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Corpora Alignment Framework for Multilingual and Robust Automatic Dialogue Evaluation
%A Wang, Xinglin
%A Shi, Jiayi
%A Yuan, Peiwen
%A Li, Kan
%Y Chen, Yun-Nung
%Y Crook, Paul
%Y Galley, Michel
%Y Ghazarian, Sarik
%Y Gunasekara, Chulaka
%Y Gupta, Raghav
%Y Hedayatnia, Behnam
%Y Kottur, Satwik
%Y Moon, Seungwhan
%Y Zhang, Chen
%S Proceedings of The Eleventh Dialog System Technology Challenge
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czech Republic
%F wang-etal-2023-parallel
%X Open-domain automatic dialogue evaluation plays an important role in dialogue systems. While recent efforts are being put into making learning-based evaluation metrics correlate better with human evaluation, robust metrics for parallel corpora and multiple domains remain unexplored. Parallel corpora refer to corpora that express the same idea in different ways (e.g., translation, paraphrasing and back-translation). In this paper, we propose Parallel Corpora Alignment Framework (PCAF), which improves the consistency and robustness of model evaluation on parallel corpora. Firstly, parallel corpora are aligned in semantic space through parallel-corpora-aligned contrastive learning. Then, parallel-corpora-aligned distillation on multi-dataset is applied to further improve model’s generalization ability across multiple data domains. Our approach ranks second on the final test data of DSTC11 track4 subtask1 (“Multilingual Automatic Evaluation Metrics”, turn-level) and third on the subtask2 (“Robust Automatic Evaluation Metrics”, turn-level), which proves the strong generalization ability and robustness of our proposed approach.
%U https://aclanthology.org/2023.dstc-1.15
%P 123-132
Markdown (Informal)
[Parallel Corpora Alignment Framework for Multilingual and Robust Automatic Dialogue Evaluation](https://aclanthology.org/2023.dstc-1.15) (Wang et al., DSTC-WS 2023)
ACL