@inproceedings{lai-etal-2021-saliency-based,
title = "Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification",
author = "Lai, Siyu and
Huang, Hui and
Jing, Dong and
Chen, Yufeng and
Xu, Jinan and
Liu, Jian",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.55",
doi = "10.18653/v1/2021.findings-emnlp.55",
pages = "599--610",
abstract = "Recent multilingual pre-trained models, like XLM-RoBERTa (XLM-R), have been demonstrated effective in many cross-lingual tasks. However, there are still gaps between the contextualized representations of similar words in different languages. To solve this problem, we propose a novel framework named Multi-View Mixed Language Training (MVMLT), which leverages code-switched data with multi-view learning to fine-tune XLM-R. MVMLT uses gradient-based saliency to extract keywords which are the most relevant to downstream tasks and replaces them with the corresponding words in the target language dynamically. Furthermore, MVMLT utilizes multi-view learning to encourage contextualized embeddings to align into a more refined language-invariant space. Extensive experiments with four languages show that our model achieves state-of-the-art results on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks, demonstrating the effectiveness of our proposed model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lai-etal-2021-saliency-based">
<titleInfo>
<title>Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyu</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Jing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent multilingual pre-trained models, like XLM-RoBERTa (XLM-R), have been demonstrated effective in many cross-lingual tasks. However, there are still gaps between the contextualized representations of similar words in different languages. To solve this problem, we propose a novel framework named Multi-View Mixed Language Training (MVMLT), which leverages code-switched data with multi-view learning to fine-tune XLM-R. MVMLT uses gradient-based saliency to extract keywords which are the most relevant to downstream tasks and replaces them with the corresponding words in the target language dynamically. Furthermore, MVMLT utilizes multi-view learning to encourage contextualized embeddings to align into a more refined language-invariant space. Extensive experiments with four languages show that our model achieves state-of-the-art results on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks, demonstrating the effectiveness of our proposed model.</abstract>
<identifier type="citekey">lai-etal-2021-saliency-based</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.55</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.55</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>599</start>
<end>610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification
%A Lai, Siyu
%A Huang, Hui
%A Jing, Dong
%A Chen, Yufeng
%A Xu, Jinan
%A Liu, Jian
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F lai-etal-2021-saliency-based
%X Recent multilingual pre-trained models, like XLM-RoBERTa (XLM-R), have been demonstrated effective in many cross-lingual tasks. However, there are still gaps between the contextualized representations of similar words in different languages. To solve this problem, we propose a novel framework named Multi-View Mixed Language Training (MVMLT), which leverages code-switched data with multi-view learning to fine-tune XLM-R. MVMLT uses gradient-based saliency to extract keywords which are the most relevant to downstream tasks and replaces them with the corresponding words in the target language dynamically. Furthermore, MVMLT utilizes multi-view learning to encourage contextualized embeddings to align into a more refined language-invariant space. Extensive experiments with four languages show that our model achieves state-of-the-art results on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks, demonstrating the effectiveness of our proposed model.
%R 10.18653/v1/2021.findings-emnlp.55
%U https://aclanthology.org/2021.findings-emnlp.55
%U https://doi.org/10.18653/v1/2021.findings-emnlp.55
%P 599-610
Markdown (Informal)
[Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification](https://aclanthology.org/2021.findings-emnlp.55) (Lai et al., Findings 2021)
ACL