@inproceedings{tran-bisazza-2019-zero,
title = "Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representations",
author = "Tran, Ke and
Bisazza, Arianna",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6132",
doi = "10.18653/v1/D19-6132",
pages = "281--288",
abstract = "We investigate whether off-the-shelf deep bidirectional sentence representations (Devlin et al., 2019) trained on a massively multilingual corpus (multilingual BERT) enable the development of an unsupervised universal dependency parser. This approach only leverages a mix of monolingual corpora in many languages and does not require any translation data making it applicable to low-resource languages. In our experiments we outperform the best CoNLL 2018 language-specific systems in all of the shared task{'}s six truly low-resource languages while using a single system. However, we also find that (i) parsing accuracy still varies dramatically when changing the training languages and (ii) in some target languages zero-shot transfer fails under all tested conditions, raising concerns on the {`}universality{'} of the whole approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-bisazza-2019-zero">
<titleInfo>
<title>Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<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>We investigate whether off-the-shelf deep bidirectional sentence representations (Devlin et al., 2019) trained on a massively multilingual corpus (multilingual BERT) enable the development of an unsupervised universal dependency parser. This approach only leverages a mix of monolingual corpora in many languages and does not require any translation data making it applicable to low-resource languages. In our experiments we outperform the best CoNLL 2018 language-specific systems in all of the shared task’s six truly low-resource languages while using a single system. However, we also find that (i) parsing accuracy still varies dramatically when changing the training languages and (ii) in some target languages zero-shot transfer fails under all tested conditions, raising concerns on the ‘universality’ of the whole approach.</abstract>
<identifier type="citekey">tran-bisazza-2019-zero</identifier>
<identifier type="doi">10.18653/v1/D19-6132</identifier>
<location>
<url>https://aclanthology.org/D19-6132</url>
</location>
<part>
<date>2019-nov</date>
<extent unit="page">
<start>281</start>
<end>288</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representations
%A Tran, Ke
%A Bisazza, Arianna
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 nov
%I Association for Computational Linguistics
%C Hong Kong, China
%F tran-bisazza-2019-zero
%X We investigate whether off-the-shelf deep bidirectional sentence representations (Devlin et al., 2019) trained on a massively multilingual corpus (multilingual BERT) enable the development of an unsupervised universal dependency parser. This approach only leverages a mix of monolingual corpora in many languages and does not require any translation data making it applicable to low-resource languages. In our experiments we outperform the best CoNLL 2018 language-specific systems in all of the shared task’s six truly low-resource languages while using a single system. However, we also find that (i) parsing accuracy still varies dramatically when changing the training languages and (ii) in some target languages zero-shot transfer fails under all tested conditions, raising concerns on the ‘universality’ of the whole approach.
%R 10.18653/v1/D19-6132
%U https://aclanthology.org/D19-6132
%U https://doi.org/10.18653/v1/D19-6132
%P 281-288
Markdown (Informal)
[Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representations](https://aclanthology.org/D19-6132) (Tran & Bisazza, EMNLP 2019)
ACL