@inproceedings{chang-etal-2022-improving,
title = "Improving Zero-Shot Multilingual Text Generation via Iterative Distillation",
author = "Chang, Ernie and
Marin, Alex and
Demberg, Vera",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.513",
pages = "5876--5881",
abstract = "The demand for multilingual dialogue systems often requires a costly labeling process, where human translators derive utterances in low resource languages from resource rich language annotation. To this end, we explore leveraging the inductive biases for target languages learned by numerous pretrained teacher models by transferring them to student models via sequence-level knowledge distillation. By assuming no target language text, the both the teacher and student models need to learn from the target distribution in a few/zero-shot manner. On the MultiATIS++ benchmark, we explore the effectiveness of our proposed technique to derive the multilingual text for 6 languages, using only the monolingual English data and the pretrained models. We show that training on the synthetic multilingual generation outputs yields close performance to training on human annotations in both slot F1 and intent accuracy; the synthetic text also scores high in naturalness and correctness based on human evaluation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chang-etal-2022-improving">
<titleInfo>
<title>Improving Zero-Shot Multilingual Text Generation via Iterative Distillation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ernie</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Marin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The demand for multilingual dialogue systems often requires a costly labeling process, where human translators derive utterances in low resource languages from resource rich language annotation. To this end, we explore leveraging the inductive biases for target languages learned by numerous pretrained teacher models by transferring them to student models via sequence-level knowledge distillation. By assuming no target language text, the both the teacher and student models need to learn from the target distribution in a few/zero-shot manner. On the MultiATIS++ benchmark, we explore the effectiveness of our proposed technique to derive the multilingual text for 6 languages, using only the monolingual English data and the pretrained models. We show that training on the synthetic multilingual generation outputs yields close performance to training on human annotations in both slot F1 and intent accuracy; the synthetic text also scores high in naturalness and correctness based on human evaluation.</abstract>
<identifier type="citekey">chang-etal-2022-improving</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.513</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5876</start>
<end>5881</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Zero-Shot Multilingual Text Generation via Iterative Distillation
%A Chang, Ernie
%A Marin, Alex
%A Demberg, Vera
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F chang-etal-2022-improving
%X The demand for multilingual dialogue systems often requires a costly labeling process, where human translators derive utterances in low resource languages from resource rich language annotation. To this end, we explore leveraging the inductive biases for target languages learned by numerous pretrained teacher models by transferring them to student models via sequence-level knowledge distillation. By assuming no target language text, the both the teacher and student models need to learn from the target distribution in a few/zero-shot manner. On the MultiATIS++ benchmark, we explore the effectiveness of our proposed technique to derive the multilingual text for 6 languages, using only the monolingual English data and the pretrained models. We show that training on the synthetic multilingual generation outputs yields close performance to training on human annotations in both slot F1 and intent accuracy; the synthetic text also scores high in naturalness and correctness based on human evaluation.
%U https://aclanthology.org/2022.coling-1.513
%P 5876-5881
Markdown (Informal)
[Improving Zero-Shot Multilingual Text Generation via Iterative Distillation](https://aclanthology.org/2022.coling-1.513) (Chang et al., COLING 2022)
ACL