@inproceedings{bao-etal-2019-low,
title = "Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations",
author = "Bao, Zuyi and
Huang, Rui and
Li, Chen and
Zhu, Kenny",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1095",
doi = "10.18653/v1/D19-1095",
pages = "1028--1039",
abstract = "Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-by-word matching. Such requirements and assumptions are infeasible for most languages, especially for languages with large linguistic distances, e.g., English and Chinese. In this work, we propose a Multilingual Language Model with deep semantic Alignment (MLMA) to generate language-independent representations for cross-lingual sequence labeling. Our methods require only monolingual corpora with no bilingual resources at all and take advantage of deep contextualized representations. Experimental results show that our approach achieves new state-of-the-art NER and POS performance across European languages, and is also effective on distant language pairs such as English and Chinese.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2019-low">
<titleInfo>
<title>Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zuyi</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenny</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-by-word matching. Such requirements and assumptions are infeasible for most languages, especially for languages with large linguistic distances, e.g., English and Chinese. In this work, we propose a Multilingual Language Model with deep semantic Alignment (MLMA) to generate language-independent representations for cross-lingual sequence labeling. Our methods require only monolingual corpora with no bilingual resources at all and take advantage of deep contextualized representations. Experimental results show that our approach achieves new state-of-the-art NER and POS performance across European languages, and is also effective on distant language pairs such as English and Chinese.</abstract>
<identifier type="citekey">bao-etal-2019-low</identifier>
<identifier type="doi">10.18653/v1/D19-1095</identifier>
<location>
<url>https://aclanthology.org/D19-1095</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1028</start>
<end>1039</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
%A Bao, Zuyi
%A Huang, Rui
%A Li, Chen
%A Zhu, Kenny
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F bao-etal-2019-low
%X Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-by-word matching. Such requirements and assumptions are infeasible for most languages, especially for languages with large linguistic distances, e.g., English and Chinese. In this work, we propose a Multilingual Language Model with deep semantic Alignment (MLMA) to generate language-independent representations for cross-lingual sequence labeling. Our methods require only monolingual corpora with no bilingual resources at all and take advantage of deep contextualized representations. Experimental results show that our approach achieves new state-of-the-art NER and POS performance across European languages, and is also effective on distant language pairs such as English and Chinese.
%R 10.18653/v1/D19-1095
%U https://aclanthology.org/D19-1095
%U https://doi.org/10.18653/v1/D19-1095
%P 1028-1039
Markdown (Informal)
[Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations](https://aclanthology.org/D19-1095) (Bao et al., EMNLP-IJCNLP 2019)
ACL