@inproceedings{spreyer-etal-2010-training,
title = "Training Parsers on Partial Trees: A Cross-language Comparison",
author = "Spreyer, Kathrin and
{\O}vrelid, Lilja and
Kuhn, Jonas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/722_Paper.pdf",
abstract = "We present a study that compares data-driven dependency parsers obtained by means of annotation projection between language pairs of varying structural similarity. We show how the partial dependency trees projected from English to Dutch, Italian and German can be exploited to train parsers for the target languages. We evaluate the parsers against manual gold standard annotations and find that the projected parsers substantially outperform our heuristic baselines by 9―25{\%} UAS, which corresponds to a 21―43{\%} reduction in error rate. A comparative error analysis focuses on how the projected target language parsers handle subjects, which is especially interesting for Italian as an instance of a pro-drop language. For Dutch, we further present experiments with German as an alternative source language. In both source languages, we contrast standard baseline parsers with parsers that are enhanced with the predictions from large-scale LFG grammars through a technique of parser stacking, and show that improvements of the source language parser can directly lead to similar improvements of the projected target language parser.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spreyer-etal-2010-training">
<titleInfo>
<title>Training Parsers on Partial Trees: A Cross-language Comparison</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kathrin</namePart>
<namePart type="family">Spreyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a study that compares data-driven dependency parsers obtained by means of annotation projection between language pairs of varying structural similarity. We show how the partial dependency trees projected from English to Dutch, Italian and German can be exploited to train parsers for the target languages. We evaluate the parsers against manual gold standard annotations and find that the projected parsers substantially outperform our heuristic baselines by 9―25% UAS, which corresponds to a 21―43% reduction in error rate. A comparative error analysis focuses on how the projected target language parsers handle subjects, which is especially interesting for Italian as an instance of a pro-drop language. For Dutch, we further present experiments with German as an alternative source language. In both source languages, we contrast standard baseline parsers with parsers that are enhanced with the predictions from large-scale LFG grammars through a technique of parser stacking, and show that improvements of the source language parser can directly lead to similar improvements of the projected target language parser.</abstract>
<identifier type="citekey">spreyer-etal-2010-training</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/722_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training Parsers on Partial Trees: A Cross-language Comparison
%A Spreyer, Kathrin
%A Øvrelid, Lilja
%A Kuhn, Jonas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F spreyer-etal-2010-training
%X We present a study that compares data-driven dependency parsers obtained by means of annotation projection between language pairs of varying structural similarity. We show how the partial dependency trees projected from English to Dutch, Italian and German can be exploited to train parsers for the target languages. We evaluate the parsers against manual gold standard annotations and find that the projected parsers substantially outperform our heuristic baselines by 9―25% UAS, which corresponds to a 21―43% reduction in error rate. A comparative error analysis focuses on how the projected target language parsers handle subjects, which is especially interesting for Italian as an instance of a pro-drop language. For Dutch, we further present experiments with German as an alternative source language. In both source languages, we contrast standard baseline parsers with parsers that are enhanced with the predictions from large-scale LFG grammars through a technique of parser stacking, and show that improvements of the source language parser can directly lead to similar improvements of the projected target language parser.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/722_Paper.pdf
Markdown (Informal)
[Training Parsers on Partial Trees: A Cross-language Comparison](http://www.lrec-conf.org/proceedings/lrec2010/pdf/722_Paper.pdf) (Spreyer et al., LREC 2010)
ACL