@inproceedings{nikolaev-etal-2020-fine,
title = "Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences",
author = "Nikolaev, Dmitry and
Arviv, Ofir and
Karidi, Taelin and
Kenneth, Neta and
Mitnik, Veronika and
Saeboe, Lilja Maria and
Abend, Omri",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.109/",
doi = "10.18653/v1/2020.acl-main.109",
pages = "1159--1176",
abstract = "The patterns in which the syntax of different languages converges and diverges are often used to inform work on cross-lingual transfer. Nevertheless, little empirical work has been done on quantifying the prevalence of different syntactic divergences across language pairs. We propose a framework for extracting divergence patterns for any language pair from a parallel corpus, building on Universal Dependencies. We show that our framework provides a detailed picture of cross-language divergences, generalizes previous approaches, and lends itself to full automation. We further present a novel dataset, a manually word-aligned subset of the Parallel UD corpus in five languages, and use it to perform a detailed corpus study. We demonstrate the usefulness of the resulting analysis by showing that it can help account for performance patterns of a cross-lingual parser."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikolaev-etal-2020-fine">
<titleInfo>
<title>Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Nikolaev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ofir</namePart>
<namePart type="family">Arviv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taelin</namePart>
<namePart type="family">Karidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neta</namePart>
<namePart type="family">Kenneth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Mitnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Saeboe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</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>The patterns in which the syntax of different languages converges and diverges are often used to inform work on cross-lingual transfer. Nevertheless, little empirical work has been done on quantifying the prevalence of different syntactic divergences across language pairs. We propose a framework for extracting divergence patterns for any language pair from a parallel corpus, building on Universal Dependencies. We show that our framework provides a detailed picture of cross-language divergences, generalizes previous approaches, and lends itself to full automation. We further present a novel dataset, a manually word-aligned subset of the Parallel UD corpus in five languages, and use it to perform a detailed corpus study. We demonstrate the usefulness of the resulting analysis by showing that it can help account for performance patterns of a cross-lingual parser.</abstract>
<identifier type="citekey">nikolaev-etal-2020-fine</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.109</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.109/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>1159</start>
<end>1176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences
%A Nikolaev, Dmitry
%A Arviv, Ofir
%A Karidi, Taelin
%A Kenneth, Neta
%A Mitnik, Veronika
%A Saeboe, Lilja Maria
%A Abend, Omri
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F nikolaev-etal-2020-fine
%X The patterns in which the syntax of different languages converges and diverges are often used to inform work on cross-lingual transfer. Nevertheless, little empirical work has been done on quantifying the prevalence of different syntactic divergences across language pairs. We propose a framework for extracting divergence patterns for any language pair from a parallel corpus, building on Universal Dependencies. We show that our framework provides a detailed picture of cross-language divergences, generalizes previous approaches, and lends itself to full automation. We further present a novel dataset, a manually word-aligned subset of the Parallel UD corpus in five languages, and use it to perform a detailed corpus study. We demonstrate the usefulness of the resulting analysis by showing that it can help account for performance patterns of a cross-lingual parser.
%R 10.18653/v1/2020.acl-main.109
%U https://aclanthology.org/2020.acl-main.109/
%U https://doi.org/10.18653/v1/2020.acl-main.109
%P 1159-1176
Markdown (Informal)
[Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences](https://aclanthology.org/2020.acl-main.109/) (Nikolaev et al., ACL 2020)
ACL
- Dmitry Nikolaev, Ofir Arviv, Taelin Karidi, Neta Kenneth, Veronika Mitnik, Lilja Maria Saeboe, and Omri Abend. 2020. Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1159–1176, Online. Association for Computational Linguistics.