@inproceedings{chau-etal-2020-parsing,
title = "Parsing with Multilingual {BERT}, a Small Corpus, and a Small Treebank",
author = "Chau, Ethan C. and
Lin, Lucy H. and
Smith, Noah A.",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.118/",
doi = "10.18653/v1/2020.findings-emnlp.118",
pages = "1324--1334",
abstract = "Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties unfamiliar to these models, whose labeled and unlabeled data is too limited to train a monolingual model effectively. We propose the use of additional language-specific pretraining and vocabulary augmentation to adapt multilingual models to low-resource settings. Using dependency parsing of four diverse low-resource language varieties as a case study, we show that these methods significantly improve performance over baselines, especially in the lowest-resource cases, and demonstrate the importance of the relationship between such models' pretraining data and target language varieties."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chau-etal-2020-parsing">
<titleInfo>
<title>Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Chau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties unfamiliar to these models, whose labeled and unlabeled data is too limited to train a monolingual model effectively. We propose the use of additional language-specific pretraining and vocabulary augmentation to adapt multilingual models to low-resource settings. Using dependency parsing of four diverse low-resource language varieties as a case study, we show that these methods significantly improve performance over baselines, especially in the lowest-resource cases, and demonstrate the importance of the relationship between such models’ pretraining data and target language varieties.</abstract>
<identifier type="citekey">chau-etal-2020-parsing</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.118</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.118/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1324</start>
<end>1334</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank
%A Chau, Ethan C.
%A Lin, Lucy H.
%A Smith, Noah A.
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F chau-etal-2020-parsing
%X Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties unfamiliar to these models, whose labeled and unlabeled data is too limited to train a monolingual model effectively. We propose the use of additional language-specific pretraining and vocabulary augmentation to adapt multilingual models to low-resource settings. Using dependency parsing of four diverse low-resource language varieties as a case study, we show that these methods significantly improve performance over baselines, especially in the lowest-resource cases, and demonstrate the importance of the relationship between such models’ pretraining data and target language varieties.
%R 10.18653/v1/2020.findings-emnlp.118
%U https://aclanthology.org/2020.findings-emnlp.118/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.118
%P 1324-1334
Markdown (Informal)
[Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank](https://aclanthology.org/2020.findings-emnlp.118/) (Chau et al., Findings 2020)
ACL