@inproceedings{zeldes-schneider-2023-ud,
title = "Are {UD} Treebanks Getting More Consistent? A Report Card for {E}nglish {UD}",
author = "Zeldes, Amir and
Schneider, Nathan",
editor = {Grobol, Lo{\"\i}c and
Tyers, Francis},
booktitle = "Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023)",
month = mar,
year = "2023",
address = "Washington, D.C.",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.udw-1.7",
pages = "58--64",
abstract = "Recent efforts to consolidate guidelines and treebanks in the Universal Dependencies project raise the expectation that joint training and dataset comparison is increasingly possible for high-resource languages such as English, which have multiple corpora. Focusing on the two largest UD English treebanks, we examine progress in data consolidation and answer several questions: Are UD English treebanks becoming more internally consistent? Are they becoming more like each other and to what extent? Is joint training a good idea, and if so, since which UD version? Our results indicate that while consolidation has made progress, joint models may still suffer from inconsistencies, which hamper their ability to leverage a larger pool of training data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeldes-schneider-2023-ud">
<titleInfo>
<title>Are UD Treebanks Getting More Consistent? A Report Card for English UD</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Grobol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Washington, D.C.</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent efforts to consolidate guidelines and treebanks in the Universal Dependencies project raise the expectation that joint training and dataset comparison is increasingly possible for high-resource languages such as English, which have multiple corpora. Focusing on the two largest UD English treebanks, we examine progress in data consolidation and answer several questions: Are UD English treebanks becoming more internally consistent? Are they becoming more like each other and to what extent? Is joint training a good idea, and if so, since which UD version? Our results indicate that while consolidation has made progress, joint models may still suffer from inconsistencies, which hamper their ability to leverage a larger pool of training data.</abstract>
<identifier type="citekey">zeldes-schneider-2023-ud</identifier>
<location>
<url>https://aclanthology.org/2023.udw-1.7</url>
</location>
<part>
<date>2023-03</date>
<extent unit="page">
<start>58</start>
<end>64</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are UD Treebanks Getting More Consistent? A Report Card for English UD
%A Zeldes, Amir
%A Schneider, Nathan
%Y Grobol, Loïc
%Y Tyers, Francis
%S Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023)
%D 2023
%8 March
%I Association for Computational Linguistics
%C Washington, D.C.
%F zeldes-schneider-2023-ud
%X Recent efforts to consolidate guidelines and treebanks in the Universal Dependencies project raise the expectation that joint training and dataset comparison is increasingly possible for high-resource languages such as English, which have multiple corpora. Focusing on the two largest UD English treebanks, we examine progress in data consolidation and answer several questions: Are UD English treebanks becoming more internally consistent? Are they becoming more like each other and to what extent? Is joint training a good idea, and if so, since which UD version? Our results indicate that while consolidation has made progress, joint models may still suffer from inconsistencies, which hamper their ability to leverage a larger pool of training data.
%U https://aclanthology.org/2023.udw-1.7
%P 58-64
Markdown (Informal)
[Are UD Treebanks Getting More Consistent? A Report Card for English UD](https://aclanthology.org/2023.udw-1.7) (Zeldes & Schneider, UDW-SyntaxFest 2023)
ACL