@inproceedings{falenska-etal-2020-grain,
title = "{GRAIN}-{S}: Manually Annotated Syntax for {G}erman Interviews",
author = {Falenska, Agnieszka and
Czesznak, Zolt{\'a}n and
Jung, Kerstin and
V{\"o}lkel, Moritz and
Seeker, Wolfgang and
Kuhn, Jonas},
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.636",
pages = "5169--5177",
abstract = "We present GRAIN-S, a set of manually created syntactic annotations for radio interviews in German. The dataset extends an existing corpus GRAIN and comes with constituency and dependency trees for six interviews. The rare combination of gold- and silver-standard annotation layers coming from GRAIN with high-quality syntax trees can serve as a useful resource for speech- and text-based research. Moreover, since interviews can be put between carefully prepared speech and spontaneous conversational speech, they cover phenomena not seen in traditional newspaper-based treebanks. Therefore, GRAIN-S can contribute to research into techniques for model adaptation and for building more corpus-independent tools. GRAIN-S follows TIGER, one of the established syntactic treebanks of German. We describe the annotation process and discuss decisions necessary to adapt the original TIGER guidelines to the interviews domain. Next, we give details on the conversion from TIGER-style trees to dependency trees. We provide data statistics and demonstrate differences between the new dataset and existing out-of-domain test sets annotated with TIGER syntactic structures. Finally, we provide baseline parsing results for further comparison.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="falenska-etal-2020-grain">
<titleInfo>
<title>GRAIN-S: Manually Annotated Syntax for German Interviews</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Falenska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoltán</namePart>
<namePart type="family">Czesznak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kerstin</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moritz</namePart>
<namePart type="family">Völkel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Seeker</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>2020-may</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 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We present GRAIN-S, a set of manually created syntactic annotations for radio interviews in German. The dataset extends an existing corpus GRAIN and comes with constituency and dependency trees for six interviews. The rare combination of gold- and silver-standard annotation layers coming from GRAIN with high-quality syntax trees can serve as a useful resource for speech- and text-based research. Moreover, since interviews can be put between carefully prepared speech and spontaneous conversational speech, they cover phenomena not seen in traditional newspaper-based treebanks. Therefore, GRAIN-S can contribute to research into techniques for model adaptation and for building more corpus-independent tools. GRAIN-S follows TIGER, one of the established syntactic treebanks of German. We describe the annotation process and discuss decisions necessary to adapt the original TIGER guidelines to the interviews domain. Next, we give details on the conversion from TIGER-style trees to dependency trees. We provide data statistics and demonstrate differences between the new dataset and existing out-of-domain test sets annotated with TIGER syntactic structures. Finally, we provide baseline parsing results for further comparison.</abstract>
<identifier type="citekey">falenska-etal-2020-grain</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.636</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>5169</start>
<end>5177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GRAIN-S: Manually Annotated Syntax for German Interviews
%A Falenska, Agnieszka
%A Czesznak, Zoltán
%A Jung, Kerstin
%A Völkel, Moritz
%A Seeker, Wolfgang
%A Kuhn, Jonas
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F falenska-etal-2020-grain
%X We present GRAIN-S, a set of manually created syntactic annotations for radio interviews in German. The dataset extends an existing corpus GRAIN and comes with constituency and dependency trees for six interviews. The rare combination of gold- and silver-standard annotation layers coming from GRAIN with high-quality syntax trees can serve as a useful resource for speech- and text-based research. Moreover, since interviews can be put between carefully prepared speech and spontaneous conversational speech, they cover phenomena not seen in traditional newspaper-based treebanks. Therefore, GRAIN-S can contribute to research into techniques for model adaptation and for building more corpus-independent tools. GRAIN-S follows TIGER, one of the established syntactic treebanks of German. We describe the annotation process and discuss decisions necessary to adapt the original TIGER guidelines to the interviews domain. Next, we give details on the conversion from TIGER-style trees to dependency trees. We provide data statistics and demonstrate differences between the new dataset and existing out-of-domain test sets annotated with TIGER syntactic structures. Finally, we provide baseline parsing results for further comparison.
%U https://aclanthology.org/2020.lrec-1.636
%P 5169-5177
Markdown (Informal)
[GRAIN-S: Manually Annotated Syntax for German Interviews](https://aclanthology.org/2020.lrec-1.636) (Falenska et al., LREC 2020)
ACL
- Agnieszka Falenska, Zoltán Czesznak, Kerstin Jung, Moritz Völkel, Wolfgang Seeker, and Jonas Kuhn. 2020. GRAIN-S: Manually Annotated Syntax for German Interviews. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 5169–5177, Marseille, France. European Language Resources Association.