@inproceedings{liu-etal-2021-mulda,
title = "{M}ul{DA}: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual {NER}",
author = "Liu, Linlin and
Ding, Bosheng and
Bing, Lidong and
Joty, Shafiq and
Si, Luo and
Miao, Chunyan",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.453",
doi = "10.18653/v1/2021.acl-long.453",
pages = "5834--5846",
abstract = "Named Entity Recognition (NER) for low-resource languages is a both practical and challenging research problem. This paper addresses zero-shot transfer for cross-lingual NER, especially when the amount of source-language training data is also limited. The paper first proposes a simple but effective labeled sequence translation method to translate source-language training data to target languages and avoids problems such as word order change and entity span determination. With the source-language data as well as the translated data, a generation-based multilingual data augmentation method is introduced to further increase diversity by generating synthetic labeled data in multiple languages. These augmented data enable the language model based NER models to generalize better with both the language-specific features from the target-language synthetic data and the language-independent features from multilingual synthetic data. An extensive set of experiments were conducted to demonstrate encouraging cross-lingual transfer performance of the new research on a wide variety of target languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-mulda">
<titleInfo>
<title>MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linlin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bosheng</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidong</namePart>
<namePart type="family">Bing</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">Luo</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyan</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entity Recognition (NER) for low-resource languages is a both practical and challenging research problem. This paper addresses zero-shot transfer for cross-lingual NER, especially when the amount of source-language training data is also limited. The paper first proposes a simple but effective labeled sequence translation method to translate source-language training data to target languages and avoids problems such as word order change and entity span determination. With the source-language data as well as the translated data, a generation-based multilingual data augmentation method is introduced to further increase diversity by generating synthetic labeled data in multiple languages. These augmented data enable the language model based NER models to generalize better with both the language-specific features from the target-language synthetic data and the language-independent features from multilingual synthetic data. An extensive set of experiments were conducted to demonstrate encouraging cross-lingual transfer performance of the new research on a wide variety of target languages.</abstract>
<identifier type="citekey">liu-etal-2021-mulda</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.453</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.453</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>5834</start>
<end>5846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER
%A Liu, Linlin
%A Ding, Bosheng
%A Bing, Lidong
%A Joty, Shafiq
%A Si, Luo
%A Miao, Chunyan
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F liu-etal-2021-mulda
%X Named Entity Recognition (NER) for low-resource languages is a both practical and challenging research problem. This paper addresses zero-shot transfer for cross-lingual NER, especially when the amount of source-language training data is also limited. The paper first proposes a simple but effective labeled sequence translation method to translate source-language training data to target languages and avoids problems such as word order change and entity span determination. With the source-language data as well as the translated data, a generation-based multilingual data augmentation method is introduced to further increase diversity by generating synthetic labeled data in multiple languages. These augmented data enable the language model based NER models to generalize better with both the language-specific features from the target-language synthetic data and the language-independent features from multilingual synthetic data. An extensive set of experiments were conducted to demonstrate encouraging cross-lingual transfer performance of the new research on a wide variety of target languages.
%R 10.18653/v1/2021.acl-long.453
%U https://aclanthology.org/2021.acl-long.453
%U https://doi.org/10.18653/v1/2021.acl-long.453
%P 5834-5846
Markdown (Informal)
[MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER](https://aclanthology.org/2021.acl-long.453) (Liu et al., ACL-IJCNLP 2021)
ACL
- Linlin Liu, Bosheng Ding, Lidong Bing, Shafiq Joty, Luo Si, and Chunyan Miao. 2021. MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5834–5846, Online. Association for Computational Linguistics.