@inproceedings{peng-zeldes-2018-roads,
title = "All Roads Lead to {UD}: Converting {S}tanford and {P}enn Parses to {E}nglish {U}niversal {D}ependencies with Multilayer Annotations",
author = "Peng, Siyao and
Zeldes, Amir",
editor = "Savary, Agata and
Ramisch, Carlos and
Hwang, Jena D. and
Schneider, Nathan and
Andresen, Melanie and
Pradhan, Sameer and
Petruck, Miriam R. L.",
booktitle = "Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions ({LAW}-{MWE}-{C}x{G}-2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-4918",
pages = "167--177",
abstract = "We describe and evaluate different approaches to the conversion of gold standard corpus data from Stanford Typed Dependencies (SD) and Penn-style constituent trees to the latest English Universal Dependencies representation (UD 2.2). Our results indicate that pure SD to UD conversion is highly accurate across multiple genres, resulting in around 1.5{\%} errors, but can be improved further to fewer than 0.5{\%} errors given access to annotations beyond the pure syntax tree, such as entity types and coreference resolution, which are necessary for correct generation of several UD relations. We show that constituent-based conversion using CoreNLP (with automatic NER) performs substantially worse in all genres, including when using gold constituent trees, primarily due to underspecification of phrasal grammatical functions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-zeldes-2018-roads">
<titleInfo>
<title>All Roads Lead to UD: Converting Stanford and Penn Parses to English Universal Dependencies with Multilayer Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyao</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Ramisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jena</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Andresen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="given">R</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Petruck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe and evaluate different approaches to the conversion of gold standard corpus data from Stanford Typed Dependencies (SD) and Penn-style constituent trees to the latest English Universal Dependencies representation (UD 2.2). Our results indicate that pure SD to UD conversion is highly accurate across multiple genres, resulting in around 1.5% errors, but can be improved further to fewer than 0.5% errors given access to annotations beyond the pure syntax tree, such as entity types and coreference resolution, which are necessary for correct generation of several UD relations. We show that constituent-based conversion using CoreNLP (with automatic NER) performs substantially worse in all genres, including when using gold constituent trees, primarily due to underspecification of phrasal grammatical functions.</abstract>
<identifier type="citekey">peng-zeldes-2018-roads</identifier>
<location>
<url>https://aclanthology.org/W18-4918</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>167</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T All Roads Lead to UD: Converting Stanford and Penn Parses to English Universal Dependencies with Multilayer Annotations
%A Peng, Siyao
%A Zeldes, Amir
%Y Savary, Agata
%Y Ramisch, Carlos
%Y Hwang, Jena D.
%Y Schneider, Nathan
%Y Andresen, Melanie
%Y Pradhan, Sameer
%Y Petruck, Miriam R. L.
%S Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F peng-zeldes-2018-roads
%X We describe and evaluate different approaches to the conversion of gold standard corpus data from Stanford Typed Dependencies (SD) and Penn-style constituent trees to the latest English Universal Dependencies representation (UD 2.2). Our results indicate that pure SD to UD conversion is highly accurate across multiple genres, resulting in around 1.5% errors, but can be improved further to fewer than 0.5% errors given access to annotations beyond the pure syntax tree, such as entity types and coreference resolution, which are necessary for correct generation of several UD relations. We show that constituent-based conversion using CoreNLP (with automatic NER) performs substantially worse in all genres, including when using gold constituent trees, primarily due to underspecification of phrasal grammatical functions.
%U https://aclanthology.org/W18-4918
%P 167-177
Markdown (Informal)
[All Roads Lead to UD: Converting Stanford and Penn Parses to English Universal Dependencies with Multilayer Annotations](https://aclanthology.org/W18-4918) (Peng & Zeldes, LAW-MWE 2018)
ACL