@inproceedings{wang-etal-2023-macedon,
title = "Macedon: Minimizing Representation Coding Rate Reduction for Cross-Lingual Natural Language Understanding",
author = "Wang, Haoyu and
Wang, Yaqing and
Yao, Huaxiu and
Gao, Jing",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.829/",
doi = "10.18653/v1/2023.findings-emnlp.829",
pages = "12426--12436",
abstract = "Cross-lingual natural language understanding(NLU) is one of the fundamental tasks of NLP. The goal is to learn a model which can generalize well on both high-resource and low-resource language data. Recent pre-trained multilingual language models, e.g., multilingual BERT, XLM, have shown impressive performance on cross-lingual NLU tasks. However, such promising results request the use of sufficient training data, which is a difficult condition to satisfy for low-resource language. When the data is limited in those low resource languages, the accuracy of existing models will drop. In light of this challenge, we investigate the important task of how to train the cross-lingual model with abundant high-source language data and limited low-resource language data. Existing methods typically learn language-agnostic representation via adversarial training and mutual information estimation. Existing approaches may suffer When data is very limited (e.g., low-resource language) because it is challenging to estimate data distribution accurately. To tackle this issue, we propose a conceptually innovative approach to remove language-associated information via \textbf{m}inimizing represent\textbf{a}tion \textbf{c}oding rate r\textbf{ed}ucti\textbf{on}(Macedon). Specifically, Macedon avoids using extra codes to encode language-related information, which is measured by the rate-distortion function. To validate the effectiveness of Macedon, we conduct extensive experiments on three tasks, including paraphrase identification, natural language inference, and query advertisement matching. The experiment results show that the proposed Macedon outperforms state-of-the-art cross-lingual NLU approaches."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-macedon">
<titleInfo>
<title>Macedon: Minimizing Representation Coding Rate Reduction for Cross-Lingual Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huaxiu</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual natural language understanding(NLU) is one of the fundamental tasks of NLP. The goal is to learn a model which can generalize well on both high-resource and low-resource language data. Recent pre-trained multilingual language models, e.g., multilingual BERT, XLM, have shown impressive performance on cross-lingual NLU tasks. However, such promising results request the use of sufficient training data, which is a difficult condition to satisfy for low-resource language. When the data is limited in those low resource languages, the accuracy of existing models will drop. In light of this challenge, we investigate the important task of how to train the cross-lingual model with abundant high-source language data and limited low-resource language data. Existing methods typically learn language-agnostic representation via adversarial training and mutual information estimation. Existing approaches may suffer When data is very limited (e.g., low-resource language) because it is challenging to estimate data distribution accurately. To tackle this issue, we propose a conceptually innovative approach to remove language-associated information via minimizing representation coding rate reduction(Macedon). Specifically, Macedon avoids using extra codes to encode language-related information, which is measured by the rate-distortion function. To validate the effectiveness of Macedon, we conduct extensive experiments on three tasks, including paraphrase identification, natural language inference, and query advertisement matching. The experiment results show that the proposed Macedon outperforms state-of-the-art cross-lingual NLU approaches.</abstract>
<identifier type="citekey">wang-etal-2023-macedon</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.829</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.829/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>12426</start>
<end>12436</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Macedon: Minimizing Representation Coding Rate Reduction for Cross-Lingual Natural Language Understanding
%A Wang, Haoyu
%A Wang, Yaqing
%A Yao, Huaxiu
%A Gao, Jing
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wang-etal-2023-macedon
%X Cross-lingual natural language understanding(NLU) is one of the fundamental tasks of NLP. The goal is to learn a model which can generalize well on both high-resource and low-resource language data. Recent pre-trained multilingual language models, e.g., multilingual BERT, XLM, have shown impressive performance on cross-lingual NLU tasks. However, such promising results request the use of sufficient training data, which is a difficult condition to satisfy for low-resource language. When the data is limited in those low resource languages, the accuracy of existing models will drop. In light of this challenge, we investigate the important task of how to train the cross-lingual model with abundant high-source language data and limited low-resource language data. Existing methods typically learn language-agnostic representation via adversarial training and mutual information estimation. Existing approaches may suffer When data is very limited (e.g., low-resource language) because it is challenging to estimate data distribution accurately. To tackle this issue, we propose a conceptually innovative approach to remove language-associated information via minimizing representation coding rate reduction(Macedon). Specifically, Macedon avoids using extra codes to encode language-related information, which is measured by the rate-distortion function. To validate the effectiveness of Macedon, we conduct extensive experiments on three tasks, including paraphrase identification, natural language inference, and query advertisement matching. The experiment results show that the proposed Macedon outperforms state-of-the-art cross-lingual NLU approaches.
%R 10.18653/v1/2023.findings-emnlp.829
%U https://aclanthology.org/2023.findings-emnlp.829/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.829
%P 12426-12436
Markdown (Informal)
[Macedon: Minimizing Representation Coding Rate Reduction for Cross-Lingual Natural Language Understanding](https://aclanthology.org/2023.findings-emnlp.829/) (Wang et al., Findings 2023)
ACL