@inproceedings{muischnek-etal-2016-estonian,
title = "{E}stonian Dependency Treebank: from Constraint Grammar tagset to {U}niversal {D}ependencies",
author = {Muischnek, Kadri and
M{\"u}{\"u}risep, Kaili and
Puolakainen, Tiina},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1247",
pages = "1558--1565",
abstract = "This paper presents the first version of Estonian Universal Dependencies Treebank which has been semi-automatically acquired from Estonian Dependency Treebank and comprises ca 400,000 words (ca 30,000 sentences) representing the genres of fiction, newspapers and scientific writing. Article analyses the differences between two annotation schemes and the conversion procedure to Universal Dependencies format. The conversion has been conducted by manually created Constraint Grammar transfer rules. As the rules enable to consider unbounded context, include lexical information and both flat and tree structure features at the same time, the method has proved to be reliable and flexible enough to handle most of transformations. The automatic conversion procedure achieved LAS 95.2{\%}, UAS 96.3{\%} and LA 98.4{\%}. If punctuation marks were excluded from the calculations, we observed LAS 96.4{\%}, UAS 97.7{\%} and LA 98.2{\%}. Still the refinement of the guidelines and methodology is needed in order to re-annotate some syntactic phenomena, e.g. inter-clausal relations. Although automatic rules usually make quite a good guess even in obscure conditions, some relations should be checked and annotated manually after the main conversion.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muischnek-etal-2016-estonian">
<titleInfo>
<title>Estonian Dependency Treebank: from Constraint Grammar tagset to Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kadri</namePart>
<namePart type="family">Muischnek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaili</namePart>
<namePart type="family">Müürisep</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiina</namePart>
<namePart type="family">Puolakainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the first version of Estonian Universal Dependencies Treebank which has been semi-automatically acquired from Estonian Dependency Treebank and comprises ca 400,000 words (ca 30,000 sentences) representing the genres of fiction, newspapers and scientific writing. Article analyses the differences between two annotation schemes and the conversion procedure to Universal Dependencies format. The conversion has been conducted by manually created Constraint Grammar transfer rules. As the rules enable to consider unbounded context, include lexical information and both flat and tree structure features at the same time, the method has proved to be reliable and flexible enough to handle most of transformations. The automatic conversion procedure achieved LAS 95.2%, UAS 96.3% and LA 98.4%. If punctuation marks were excluded from the calculations, we observed LAS 96.4%, UAS 97.7% and LA 98.2%. Still the refinement of the guidelines and methodology is needed in order to re-annotate some syntactic phenomena, e.g. inter-clausal relations. Although automatic rules usually make quite a good guess even in obscure conditions, some relations should be checked and annotated manually after the main conversion.</abstract>
<identifier type="citekey">muischnek-etal-2016-estonian</identifier>
<location>
<url>https://aclanthology.org/L16-1247</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1558</start>
<end>1565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Estonian Dependency Treebank: from Constraint Grammar tagset to Universal Dependencies
%A Muischnek, Kadri
%A Müürisep, Kaili
%A Puolakainen, Tiina
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F muischnek-etal-2016-estonian
%X This paper presents the first version of Estonian Universal Dependencies Treebank which has been semi-automatically acquired from Estonian Dependency Treebank and comprises ca 400,000 words (ca 30,000 sentences) representing the genres of fiction, newspapers and scientific writing. Article analyses the differences between two annotation schemes and the conversion procedure to Universal Dependencies format. The conversion has been conducted by manually created Constraint Grammar transfer rules. As the rules enable to consider unbounded context, include lexical information and both flat and tree structure features at the same time, the method has proved to be reliable and flexible enough to handle most of transformations. The automatic conversion procedure achieved LAS 95.2%, UAS 96.3% and LA 98.4%. If punctuation marks were excluded from the calculations, we observed LAS 96.4%, UAS 97.7% and LA 98.2%. Still the refinement of the guidelines and methodology is needed in order to re-annotate some syntactic phenomena, e.g. inter-clausal relations. Although automatic rules usually make quite a good guess even in obscure conditions, some relations should be checked and annotated manually after the main conversion.
%U https://aclanthology.org/L16-1247
%P 1558-1565
Markdown (Informal)
[Estonian Dependency Treebank: from Constraint Grammar tagset to Universal Dependencies](https://aclanthology.org/L16-1247) (Muischnek et al., LREC 2016)
ACL