@inproceedings{gou-etal-2023-cross,
title = "Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages",
author = "Gou, Qi and
Xia, Zehua and
Du, Wenzhe",
editor = "Muresan, Smaranda and
Chen, Vivian and
Casey, Kennington and
David, Vandyke and
Nina, Dethlefs and
Koji, Inoue and
Erik, Ekstedt and
Stefan, Ultes",
booktitle = "Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.dialdoc-1.1",
doi = "10.18653/v1/2023.dialdoc-1.1",
pages = "1--7",
abstract = "This paper proposes a framework to address the issue of data scarcity in Document-Grounded Dialogue Systems(DGDS). Our model leverages high-resource languages to enhance the capability of dialogue generation in low-resource languages. Specifically, We present a novel pipeline CLEM (Cross-Lingual Enhanced Model) including adversarial training retrieval (Retriever and Re-ranker), and Fid (fusion-in-decoder) generator. To further leverage high-resource language, we also propose an innovative architecture to conduct alignment across different languages with translated training. Extensive experiment results demonstrate the effectiveness of our model and we achieved 4th place in the DialDoc 2023 Competition. Therefore, CLEM can serve as a solution to resource scarcity in DGDS and provide useful guidance for multi-lingual alignment tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gou-etal-2023-cross">
<titleInfo>
<title>Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Gou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zehua</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenzhe</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kennington</namePart>
<namePart type="family">Casey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandyke</namePart>
<namePart type="family">David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dethlefs</namePart>
<namePart type="family">Nina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inoue</namePart>
<namePart type="family">Koji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekstedt</namePart>
<namePart type="family">Erik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ultes</namePart>
<namePart type="family">Stefan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes a framework to address the issue of data scarcity in Document-Grounded Dialogue Systems(DGDS). Our model leverages high-resource languages to enhance the capability of dialogue generation in low-resource languages. Specifically, We present a novel pipeline CLEM (Cross-Lingual Enhanced Model) including adversarial training retrieval (Retriever and Re-ranker), and Fid (fusion-in-decoder) generator. To further leverage high-resource language, we also propose an innovative architecture to conduct alignment across different languages with translated training. Extensive experiment results demonstrate the effectiveness of our model and we achieved 4th place in the DialDoc 2023 Competition. Therefore, CLEM can serve as a solution to resource scarcity in DGDS and provide useful guidance for multi-lingual alignment tasks.</abstract>
<identifier type="citekey">gou-etal-2023-cross</identifier>
<identifier type="doi">10.18653/v1/2023.dialdoc-1.1</identifier>
<location>
<url>https://aclanthology.org/2023.dialdoc-1.1</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1</start>
<end>7</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages
%A Gou, Qi
%A Xia, Zehua
%A Du, Wenzhe
%Y Muresan, Smaranda
%Y Chen, Vivian
%Y Casey, Kennington
%Y David, Vandyke
%Y Nina, Dethlefs
%Y Koji, Inoue
%Y Erik, Ekstedt
%Y Stefan, Ultes
%S Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F gou-etal-2023-cross
%X This paper proposes a framework to address the issue of data scarcity in Document-Grounded Dialogue Systems(DGDS). Our model leverages high-resource languages to enhance the capability of dialogue generation in low-resource languages. Specifically, We present a novel pipeline CLEM (Cross-Lingual Enhanced Model) including adversarial training retrieval (Retriever and Re-ranker), and Fid (fusion-in-decoder) generator. To further leverage high-resource language, we also propose an innovative architecture to conduct alignment across different languages with translated training. Extensive experiment results demonstrate the effectiveness of our model and we achieved 4th place in the DialDoc 2023 Competition. Therefore, CLEM can serve as a solution to resource scarcity in DGDS and provide useful guidance for multi-lingual alignment tasks.
%R 10.18653/v1/2023.dialdoc-1.1
%U https://aclanthology.org/2023.dialdoc-1.1
%U https://doi.org/10.18653/v1/2023.dialdoc-1.1
%P 1-7
Markdown (Informal)
[Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages](https://aclanthology.org/2023.dialdoc-1.1) (Gou et al., dialdoc 2023)
ACL