@inproceedings{turk-etal-2019-turkish,
title = "{T}urkish Treebanking: Unifying and Constructing Efforts",
author = {T{\"u}rk, Utku and
Atmaca, Furkan and
{\"O}zate{\c{s}}, {\c{S}}aziye Bet{\"u}l and
K{\"o}ksal, Abdullatif and
Ozturk Basaran, Balkiz and
Gungor, Tunga and
{\"O}zg{\"u}r, Arzucan},
editor = "Friedrich, Annemarie and
Zeyrek, Deniz and
Hoek, Jet",
booktitle = "Proceedings of the 13th Linguistic Annotation Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4019/",
doi = "10.18653/v1/W19-4019",
pages = "166--177",
abstract = {In this paper, we present the current version of two different treebanks, the re-annotation of the Turkish PUD Treebank and the first annotation of the Turkish National Corpus Universal Dependency (henceforth TNC-UD). The annotation of both treebanks, the Turkish PUD Treebank and TNC-UD, was carried out based on the decisions concerning linguistic adequacy of re-annotation of the Turkish IMST-UD Treebank (T{\"u}rk et. al., forthcoming). Both of the treebanks were annotated with the same annotation process and morphological and syntactic analyses. The TNC-UD is planned to have 10,000 sentences. In this paper, we will present the first 500 sentences along with the annotation PUD Treebank. Moreover, this paper also offers the parsing results of a graph-based neural parser on the previous and re-annotated PUD, as well as the TNC-UD. In light of the comparisons, even though we observe a slight decrease in the attachment scores of the Turkish PUD treebank, we demonstrate that the annotation of the TNC-UD improves the parsing accuracy of Turkish. In addition to the treebanks, we have also constructed a custom annotation software with advanced filtering and morphological editing options. Both the treebanks, including a full edit-history and the annotation guidelines, and the custom software are publicly available under an open license online.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="turk-etal-2019-turkish">
<titleInfo>
<title>Turkish Treebanking: Unifying and Constructing Efforts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Utku</namePart>
<namePart type="family">Türk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furkan</namePart>
<namePart type="family">Atmaca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Şaziye</namePart>
<namePart type="given">Betül</namePart>
<namePart type="family">Özateş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullatif</namePart>
<namePart type="family">Köksal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balkiz</namePart>
<namePart type="family">Ozturk Basaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tunga</namePart>
<namePart type="family">Gungor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arzucan</namePart>
<namePart type="family">Özgür</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Linguistic Annotation Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deniz</namePart>
<namePart type="family">Zeyrek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jet</namePart>
<namePart type="family">Hoek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the current version of two different treebanks, the re-annotation of the Turkish PUD Treebank and the first annotation of the Turkish National Corpus Universal Dependency (henceforth TNC-UD). The annotation of both treebanks, the Turkish PUD Treebank and TNC-UD, was carried out based on the decisions concerning linguistic adequacy of re-annotation of the Turkish IMST-UD Treebank (Türk et. al., forthcoming). Both of the treebanks were annotated with the same annotation process and morphological and syntactic analyses. The TNC-UD is planned to have 10,000 sentences. In this paper, we will present the first 500 sentences along with the annotation PUD Treebank. Moreover, this paper also offers the parsing results of a graph-based neural parser on the previous and re-annotated PUD, as well as the TNC-UD. In light of the comparisons, even though we observe a slight decrease in the attachment scores of the Turkish PUD treebank, we demonstrate that the annotation of the TNC-UD improves the parsing accuracy of Turkish. In addition to the treebanks, we have also constructed a custom annotation software with advanced filtering and morphological editing options. Both the treebanks, including a full edit-history and the annotation guidelines, and the custom software are publicly available under an open license online.</abstract>
<identifier type="citekey">turk-etal-2019-turkish</identifier>
<identifier type="doi">10.18653/v1/W19-4019</identifier>
<location>
<url>https://aclanthology.org/W19-4019/</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>166</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Turkish Treebanking: Unifying and Constructing Efforts
%A Türk, Utku
%A Atmaca, Furkan
%A Özateş, Şaziye Betül
%A Köksal, Abdullatif
%A Ozturk Basaran, Balkiz
%A Gungor, Tunga
%A Özgür, Arzucan
%Y Friedrich, Annemarie
%Y Zeyrek, Deniz
%Y Hoek, Jet
%S Proceedings of the 13th Linguistic Annotation Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F turk-etal-2019-turkish
%X In this paper, we present the current version of two different treebanks, the re-annotation of the Turkish PUD Treebank and the first annotation of the Turkish National Corpus Universal Dependency (henceforth TNC-UD). The annotation of both treebanks, the Turkish PUD Treebank and TNC-UD, was carried out based on the decisions concerning linguistic adequacy of re-annotation of the Turkish IMST-UD Treebank (Türk et. al., forthcoming). Both of the treebanks were annotated with the same annotation process and morphological and syntactic analyses. The TNC-UD is planned to have 10,000 sentences. In this paper, we will present the first 500 sentences along with the annotation PUD Treebank. Moreover, this paper also offers the parsing results of a graph-based neural parser on the previous and re-annotated PUD, as well as the TNC-UD. In light of the comparisons, even though we observe a slight decrease in the attachment scores of the Turkish PUD treebank, we demonstrate that the annotation of the TNC-UD improves the parsing accuracy of Turkish. In addition to the treebanks, we have also constructed a custom annotation software with advanced filtering and morphological editing options. Both the treebanks, including a full edit-history and the annotation guidelines, and the custom software are publicly available under an open license online.
%R 10.18653/v1/W19-4019
%U https://aclanthology.org/W19-4019/
%U https://doi.org/10.18653/v1/W19-4019
%P 166-177
Markdown (Informal)
[Turkish Treebanking: Unifying and Constructing Efforts](https://aclanthology.org/W19-4019/) (Türk et al., LAW 2019)
ACL
- Utku Türk, Furkan Atmaca, Şaziye Betül Özateş, Abdullatif Köksal, Balkiz Ozturk Basaran, Tunga Gungor, and Arzucan Özgür. 2019. Turkish Treebanking: Unifying and Constructing Efforts. In Proceedings of the 13th Linguistic Annotation Workshop, pages 166–177, Florence, Italy. Association for Computational Linguistics.