@inproceedings{kuzgun-etal-2021-constituency,
title = "From Constituency to {UD}-Style Dependency: Building the First Conversion Tool of {T}urkish",
author = {Kuzgun, Asl{\i} and
Y{\i}ld{\i}z, O{\u{g}}uz Kerem and
Cesur, Neslihan and
Mar{\c{s}}an, B{\"u}{\c{s}}ra and
Yenice, Arife Bet{\"u}l and
San{\i}yar, Ezgi and
Kuyruk{\c{c}}u, Oguzhan and
Ar{\i}can, Bilge Nas and
Y{\i}ld{\i}z, Olcay Taner},
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
month = sep,
year = "2021",
address = "Held Online",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/2021.ranlp-1.87/",
pages = "761--769",
abstract = "This paper deliberates on the process of building the first constituency-to-dependency conversion tool of Turkish. The starting point of this work is a previous study in which 10,000 phrase structure trees were manually transformed into Turkish from the original PennTreebank corpus. Within the scope of this project, these Turkish phrase structure trees were automatically converted into UD-style dependency structures, using both a rule-based algorithm and a machine learning algorithm specific to the requirements of the Turkish language. The results of both algorithms were compared and the machine learning approach proved to be more accurate than the rule-based algorithm. The output was revised by a team of linguists. The refined versions were taken as gold standard annotations for the evaluation of the algorithms. In addition to its contribution to the UD Project with a large dataset of 10,000 Turkish dependency trees, this project also fulfills the important gap of a Turkish conversion tool, enabling the quick compilation of dependency corpora which can be used for the training of better dependency parsers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuzgun-etal-2021-constituency">
<titleInfo>
<title>From Constituency to UD-Style Dependency: Building the First Conversion Tool of Turkish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aslı</namePart>
<namePart type="family">Kuzgun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oğuz</namePart>
<namePart type="given">Kerem</namePart>
<namePart type="family">Yıldız</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neslihan</namePart>
<namePart type="family">Cesur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Büşra</namePart>
<namePart type="family">Marşan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arife</namePart>
<namePart type="given">Betül</namePart>
<namePart type="family">Yenice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ezgi</namePart>
<namePart type="family">Sanıyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oguzhan</namePart>
<namePart type="family">Kuyrukçu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bilge</namePart>
<namePart type="given">Nas</namePart>
<namePart type="family">Arıcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olcay</namePart>
<namePart type="given">Taner</namePart>
<namePart type="family">Yıldız</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Held Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper deliberates on the process of building the first constituency-to-dependency conversion tool of Turkish. The starting point of this work is a previous study in which 10,000 phrase structure trees were manually transformed into Turkish from the original PennTreebank corpus. Within the scope of this project, these Turkish phrase structure trees were automatically converted into UD-style dependency structures, using both a rule-based algorithm and a machine learning algorithm specific to the requirements of the Turkish language. The results of both algorithms were compared and the machine learning approach proved to be more accurate than the rule-based algorithm. The output was revised by a team of linguists. The refined versions were taken as gold standard annotations for the evaluation of the algorithms. In addition to its contribution to the UD Project with a large dataset of 10,000 Turkish dependency trees, this project also fulfills the important gap of a Turkish conversion tool, enabling the quick compilation of dependency corpora which can be used for the training of better dependency parsers.</abstract>
<identifier type="citekey">kuzgun-etal-2021-constituency</identifier>
<location>
<url>https://aclanthology.org/2021.ranlp-1.87/</url>
</location>
<part>
<date>2021-09</date>
<extent unit="page">
<start>761</start>
<end>769</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Constituency to UD-Style Dependency: Building the First Conversion Tool of Turkish
%A Kuzgun, Aslı
%A Yıldız, Oğuz Kerem
%A Cesur, Neslihan
%A Marşan, Büşra
%A Yenice, Arife Betül
%A Sanıyar, Ezgi
%A Kuyrukçu, Oguzhan
%A Arıcan, Bilge Nas
%A Yıldız, Olcay Taner
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F kuzgun-etal-2021-constituency
%X This paper deliberates on the process of building the first constituency-to-dependency conversion tool of Turkish. The starting point of this work is a previous study in which 10,000 phrase structure trees were manually transformed into Turkish from the original PennTreebank corpus. Within the scope of this project, these Turkish phrase structure trees were automatically converted into UD-style dependency structures, using both a rule-based algorithm and a machine learning algorithm specific to the requirements of the Turkish language. The results of both algorithms were compared and the machine learning approach proved to be more accurate than the rule-based algorithm. The output was revised by a team of linguists. The refined versions were taken as gold standard annotations for the evaluation of the algorithms. In addition to its contribution to the UD Project with a large dataset of 10,000 Turkish dependency trees, this project also fulfills the important gap of a Turkish conversion tool, enabling the quick compilation of dependency corpora which can be used for the training of better dependency parsers.
%U https://aclanthology.org/2021.ranlp-1.87/
%P 761-769
Markdown (Informal)
[From Constituency to UD-Style Dependency: Building the First Conversion Tool of Turkish](https://aclanthology.org/2021.ranlp-1.87/) (Kuzgun et al., RANLP 2021)
ACL
- Aslı Kuzgun, Oğuz Kerem Yıldız, Neslihan Cesur, Büşra Marşan, Arife Betül Yenice, Ezgi Sanıyar, Oguzhan Kuyrukçu, Bilge Nas Arıcan, and Olcay Taner Yıldız. 2021. From Constituency to UD-Style Dependency: Building the First Conversion Tool of Turkish. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 761–769, Held Online. INCOMA Ltd..