@inproceedings{tu-etal-2024-efficiently,
title = "Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning",
author = "Tu, Lifu and
Qu, Jin and
Yavuz, Semih and
Joty, Shafiq and
Liu, Wenhao and
Xiong, Caiming and
Zhou, Yingbo",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-eacl.85",
pages = "1278--1294",
abstract = "Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rather limited. This is partly due to the high cost of obtaining non-English conversational data, which results in limited coverage. In this work, we introduce for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset that we created by translating the English-only Schema-Guided Dialogue (SGD) dataset (Rastogi et al., 2020) into 105 other languages. XSGD contains about 330k utterances per language. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts. We also investigate two different classifiers: NLI-based and vanilla classifiers, and test cross-lingual capability enabled by the aligned prompts. We evaluate our model{'}s cross-lingual generalization capabilities on two conversation tasks: slot-filling and intent classification. Our results demonstrate strong and efficient modeling ability of NLI-based classifiers and the large cross-lingual transfer improvements achieved by our aligned prompts, particularly in few-shot settings. We also conduct studies on large language models (LLMs) such as text-davinci-003 and ChatGPT in both zero- and few-shot settings. While LLMs exhibit impressive performance in English, their cross-lingual capabilities in other languages, particularly low-resource ones, are limited.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2024-efficiently">
<titleInfo>
<title>Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifu</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Semih</namePart>
<namePart type="family">Yavuz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingbo</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rather limited. This is partly due to the high cost of obtaining non-English conversational data, which results in limited coverage. In this work, we introduce for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset that we created by translating the English-only Schema-Guided Dialogue (SGD) dataset (Rastogi et al., 2020) into 105 other languages. XSGD contains about 330k utterances per language. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts. We also investigate two different classifiers: NLI-based and vanilla classifiers, and test cross-lingual capability enabled by the aligned prompts. We evaluate our model’s cross-lingual generalization capabilities on two conversation tasks: slot-filling and intent classification. Our results demonstrate strong and efficient modeling ability of NLI-based classifiers and the large cross-lingual transfer improvements achieved by our aligned prompts, particularly in few-shot settings. We also conduct studies on large language models (LLMs) such as text-davinci-003 and ChatGPT in both zero- and few-shot settings. While LLMs exhibit impressive performance in English, their cross-lingual capabilities in other languages, particularly low-resource ones, are limited.</abstract>
<identifier type="citekey">tu-etal-2024-efficiently</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.85</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1278</start>
<end>1294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
%A Tu, Lifu
%A Qu, Jin
%A Yavuz, Semih
%A Joty, Shafiq
%A Liu, Wenhao
%A Xiong, Caiming
%A Zhou, Yingbo
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F tu-etal-2024-efficiently
%X Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rather limited. This is partly due to the high cost of obtaining non-English conversational data, which results in limited coverage. In this work, we introduce for cross-lingual alignment pretraining, a parallel and large-scale multilingual conversation dataset that we created by translating the English-only Schema-Guided Dialogue (SGD) dataset (Rastogi et al., 2020) into 105 other languages. XSGD contains about 330k utterances per language. To facilitate aligned cross-lingual representations, we develop an efficient prompt-tuning-based method for learning alignment prompts. We also investigate two different classifiers: NLI-based and vanilla classifiers, and test cross-lingual capability enabled by the aligned prompts. We evaluate our model’s cross-lingual generalization capabilities on two conversation tasks: slot-filling and intent classification. Our results demonstrate strong and efficient modeling ability of NLI-based classifiers and the large cross-lingual transfer improvements achieved by our aligned prompts, particularly in few-shot settings. We also conduct studies on large language models (LLMs) such as text-davinci-003 and ChatGPT in both zero- and few-shot settings. While LLMs exhibit impressive performance in English, their cross-lingual capabilities in other languages, particularly low-resource ones, are limited.
%U https://aclanthology.org/2024.findings-eacl.85
%P 1278-1294
Markdown (Informal)
[Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning](https://aclanthology.org/2024.findings-eacl.85) (Tu et al., Findings 2024)
ACL