@inproceedings{silveira-etal-2014-gold,
title = "A Gold Standard Dependency Corpus for {E}nglish",
author = "Silveira, Natalia and
Dozat, Timothy and
de Marneffe, Marie-Catherine and
Bowman, Samuel and
Connor, Miriam and
Bauer, John and
Manning, Chris",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/1089_Paper.pdf",
pages = "2897--2904",
abstract = "We present a gold standard annotation of syntactic dependencies in the English Web Treebank corpus using the Stanford Dependencies formalism. This resource addresses the lack of a gold standard dependency treebank for English, as well as the limited availability of gold standard syntactic annotations for English informal text genres. We also present experiments on the use of this resource, both for training dependency parsers and for evaluating the quality of different versions of the Stanford Parser, which includes a converter tool to produce dependency annotation from constituency trees. We show that training a dependency parser on a mix of newswire and web data leads to better performance on that type of data without hurting performance on newswire text, and therefore gold standard annotations for non-canonical text can be a valuable resource for parsing. Furthermore, the systematic annotation effort has informed both the SD formalism and its implementation in the Stanford Parser{'}s dependency converter. In response to the challenges encountered by annotators in the EWT corpus, the formalism has been revised and extended, and the converter has been improved.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silveira-etal-2014-gold">
<titleInfo>
<title>A Gold Standard Dependency Corpus for English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Silveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Dozat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Bowman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Bauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Manning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a gold standard annotation of syntactic dependencies in the English Web Treebank corpus using the Stanford Dependencies formalism. This resource addresses the lack of a gold standard dependency treebank for English, as well as the limited availability of gold standard syntactic annotations for English informal text genres. We also present experiments on the use of this resource, both for training dependency parsers and for evaluating the quality of different versions of the Stanford Parser, which includes a converter tool to produce dependency annotation from constituency trees. We show that training a dependency parser on a mix of newswire and web data leads to better performance on that type of data without hurting performance on newswire text, and therefore gold standard annotations for non-canonical text can be a valuable resource for parsing. Furthermore, the systematic annotation effort has informed both the SD formalism and its implementation in the Stanford Parser’s dependency converter. In response to the challenges encountered by annotators in the EWT corpus, the formalism has been revised and extended, and the converter has been improved.</abstract>
<identifier type="citekey">silveira-etal-2014-gold</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1089_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2897</start>
<end>2904</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Gold Standard Dependency Corpus for English
%A Silveira, Natalia
%A Dozat, Timothy
%A de Marneffe, Marie-Catherine
%A Bowman, Samuel
%A Connor, Miriam
%A Bauer, John
%A Manning, Chris
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F silveira-etal-2014-gold
%X We present a gold standard annotation of syntactic dependencies in the English Web Treebank corpus using the Stanford Dependencies formalism. This resource addresses the lack of a gold standard dependency treebank for English, as well as the limited availability of gold standard syntactic annotations for English informal text genres. We also present experiments on the use of this resource, both for training dependency parsers and for evaluating the quality of different versions of the Stanford Parser, which includes a converter tool to produce dependency annotation from constituency trees. We show that training a dependency parser on a mix of newswire and web data leads to better performance on that type of data without hurting performance on newswire text, and therefore gold standard annotations for non-canonical text can be a valuable resource for parsing. Furthermore, the systematic annotation effort has informed both the SD formalism and its implementation in the Stanford Parser’s dependency converter. In response to the challenges encountered by annotators in the EWT corpus, the formalism has been revised and extended, and the converter has been improved.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1089_Paper.pdf
%P 2897-2904
Markdown (Informal)
[A Gold Standard Dependency Corpus for English](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1089_Paper.pdf) (Silveira et al., LREC 2014)
ACL
- Natalia Silveira, Timothy Dozat, Marie-Catherine de Marneffe, Samuel Bowman, Miriam Connor, John Bauer, and Chris Manning. 2014. A Gold Standard Dependency Corpus for English. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2897–2904, Reykjavik, Iceland. European Language Resources Association (ELRA).