@inproceedings{moradshahi-etal-2023-zero,
title = "Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation",
author = "Moradshahi, Mehrad and
Semnani, Sina and
Lam, Monica",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.62",
doi = "10.18653/v1/2023.eacl-main.62",
pages = "886--901",
abstract = "Task-oriented Dialogue (ToD) agents are mostly limited to a few widely-spoken languages, mainly due to the high cost of acquiring training data for each language. Existing low-cost approaches that rely on cross-lingual embeddings or naive machine translation sacrifice a lot of accuracy for data efficiency, and largely fail in creating a usable dialogue agent. We propose automatic methods that use ToD training data in a source language to build a high-quality functioning dialogue agent in another target language that has no training data (i.e. zero-shot) or a small training set (i.e. few-shot). Unlike most prior work in cross-lingual ToD that only focuses on Dialogue State Tracking (DST), we build an end-to-end agent. We show that our approach closes the accuracy gap between few-shot and existing full-shot methods for ToD agents. We achieve this by (1) improving the dialogue data representation, (2) improving entity-aware machine translation, and (3) automatic filtering of noisy translations. We evaluate our approach on the recent bilingual dialogue dataset BiToD.In Chinese to English transfer, in the zero-shot setting, our method achieves 46.7{\%} and 22.0{\%} in Task Success Rate (TSR) and Dialogue Success Rate (DSR) respectively. In the few-shot setting where 10{\%} of the data in the target language is used, we improve the state-of-the-art by 15.2{\%} and 14.0{\%}, coming within 5{\%} of full-shot training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moradshahi-etal-2023-zero">
<titleInfo>
<title>Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mehrad</namePart>
<namePart type="family">Moradshahi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Semnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Task-oriented Dialogue (ToD) agents are mostly limited to a few widely-spoken languages, mainly due to the high cost of acquiring training data for each language. Existing low-cost approaches that rely on cross-lingual embeddings or naive machine translation sacrifice a lot of accuracy for data efficiency, and largely fail in creating a usable dialogue agent. We propose automatic methods that use ToD training data in a source language to build a high-quality functioning dialogue agent in another target language that has no training data (i.e. zero-shot) or a small training set (i.e. few-shot). Unlike most prior work in cross-lingual ToD that only focuses on Dialogue State Tracking (DST), we build an end-to-end agent. We show that our approach closes the accuracy gap between few-shot and existing full-shot methods for ToD agents. We achieve this by (1) improving the dialogue data representation, (2) improving entity-aware machine translation, and (3) automatic filtering of noisy translations. We evaluate our approach on the recent bilingual dialogue dataset BiToD.In Chinese to English transfer, in the zero-shot setting, our method achieves 46.7% and 22.0% in Task Success Rate (TSR) and Dialogue Success Rate (DSR) respectively. In the few-shot setting where 10% of the data in the target language is used, we improve the state-of-the-art by 15.2% and 14.0%, coming within 5% of full-shot training.</abstract>
<identifier type="citekey">moradshahi-etal-2023-zero</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.62</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.62</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>886</start>
<end>901</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation
%A Moradshahi, Mehrad
%A Semnani, Sina
%A Lam, Monica
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F moradshahi-etal-2023-zero
%X Task-oriented Dialogue (ToD) agents are mostly limited to a few widely-spoken languages, mainly due to the high cost of acquiring training data for each language. Existing low-cost approaches that rely on cross-lingual embeddings or naive machine translation sacrifice a lot of accuracy for data efficiency, and largely fail in creating a usable dialogue agent. We propose automatic methods that use ToD training data in a source language to build a high-quality functioning dialogue agent in another target language that has no training data (i.e. zero-shot) or a small training set (i.e. few-shot). Unlike most prior work in cross-lingual ToD that only focuses on Dialogue State Tracking (DST), we build an end-to-end agent. We show that our approach closes the accuracy gap between few-shot and existing full-shot methods for ToD agents. We achieve this by (1) improving the dialogue data representation, (2) improving entity-aware machine translation, and (3) automatic filtering of noisy translations. We evaluate our approach on the recent bilingual dialogue dataset BiToD.In Chinese to English transfer, in the zero-shot setting, our method achieves 46.7% and 22.0% in Task Success Rate (TSR) and Dialogue Success Rate (DSR) respectively. In the few-shot setting where 10% of the data in the target language is used, we improve the state-of-the-art by 15.2% and 14.0%, coming within 5% of full-shot training.
%R 10.18653/v1/2023.eacl-main.62
%U https://aclanthology.org/2023.eacl-main.62
%U https://doi.org/10.18653/v1/2023.eacl-main.62
%P 886-901
Markdown (Informal)
[Zero and Few-Shot Localization of Task-Oriented Dialogue Agents with a Distilled Representation](https://aclanthology.org/2023.eacl-main.62) (Moradshahi et al., EACL 2023)
ACL