@inproceedings{fankhauser-etal-2020-evaluating,
title = "Evaluating a Dependency Parser on {D}e{R}e{K}o",
author = "Fankhauser, Peter and
Do, Bich-Ngoc and
Kupietz, Marc",
editor = {Ba{\'n}ski, Piotr and
Barbaresi, Adrien and
Clematide, Simon and
Kupietz, Marc and
L{\"u}ngen, Harald and
Pisetta, Ines},
booktitle = "Proceedings of the 8th Workshop on Challenges in the Management of Large Corpora",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Ressources Association",
url = "https://aclanthology.org/2020.cmlc-1.2",
pages = "10--14",
abstract = "We evaluate a graph-based dependency parser on DeReKo, a large corpus of contemporary German. The dependency parser is trained on the German dataset from the SPMRL 2014 Shared Task which contains text from the news domain, whereas DeReKo also covers other domains including fiction, science, and technology. To avoid the need for costly manual annotation of the corpus, we use the parser{'}s probability estimates for unlabeled and labeled attachment as main evaluation criterion. We show that these probability estimates are highly correlated with the actual attachment scores on a manually annotated test set. On this basis, we compare estimated parsing scores for the individual domains in DeReKo, and show that the scores decrease with increasing distance of a domain to the training corpus.",
language = "English",
ISBN = "979-10-95546-61-0",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fankhauser-etal-2020-evaluating">
<titleInfo>
<title>Evaluating a Dependency Parser on DeReKo</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Fankhauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bich-Ngoc</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Challenges in the Management of Large Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Bański</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrien</namePart>
<namePart type="family">Barbaresi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Clematide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harald</namePart>
<namePart type="family">Lüngen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ines</namePart>
<namePart type="family">Pisetta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Ressources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-61-0</identifier>
</relatedItem>
<abstract>We evaluate a graph-based dependency parser on DeReKo, a large corpus of contemporary German. The dependency parser is trained on the German dataset from the SPMRL 2014 Shared Task which contains text from the news domain, whereas DeReKo also covers other domains including fiction, science, and technology. To avoid the need for costly manual annotation of the corpus, we use the parser’s probability estimates for unlabeled and labeled attachment as main evaluation criterion. We show that these probability estimates are highly correlated with the actual attachment scores on a manually annotated test set. On this basis, we compare estimated parsing scores for the individual domains in DeReKo, and show that the scores decrease with increasing distance of a domain to the training corpus.</abstract>
<identifier type="citekey">fankhauser-etal-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.cmlc-1.2</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>10</start>
<end>14</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating a Dependency Parser on DeReKo
%A Fankhauser, Peter
%A Do, Bich-Ngoc
%A Kupietz, Marc
%Y Bański, Piotr
%Y Barbaresi, Adrien
%Y Clematide, Simon
%Y Kupietz, Marc
%Y Lüngen, Harald
%Y Pisetta, Ines
%S Proceedings of the 8th Workshop on Challenges in the Management of Large Corpora
%D 2020
%8 May
%I European Language Ressources Association
%C Marseille, France
%@ 979-10-95546-61-0
%G English
%F fankhauser-etal-2020-evaluating
%X We evaluate a graph-based dependency parser on DeReKo, a large corpus of contemporary German. The dependency parser is trained on the German dataset from the SPMRL 2014 Shared Task which contains text from the news domain, whereas DeReKo also covers other domains including fiction, science, and technology. To avoid the need for costly manual annotation of the corpus, we use the parser’s probability estimates for unlabeled and labeled attachment as main evaluation criterion. We show that these probability estimates are highly correlated with the actual attachment scores on a manually annotated test set. On this basis, we compare estimated parsing scores for the individual domains in DeReKo, and show that the scores decrease with increasing distance of a domain to the training corpus.
%U https://aclanthology.org/2020.cmlc-1.2
%P 10-14
Markdown (Informal)
[Evaluating a Dependency Parser on DeReKo](https://aclanthology.org/2020.cmlc-1.2) (Fankhauser et al., CMLC 2020)
ACL
- Peter Fankhauser, Bich-Ngoc Do, and Marc Kupietz. 2020. Evaluating a Dependency Parser on DeReKo. In Proceedings of the 8th Workshop on Challenges in the Management of Large Corpora, pages 10–14, Marseille, France. European Language Ressources Association.