@inproceedings{bolucu-can-2022-turkish,
title = "{T}urkish {U}niversal {C}onceptual {C}ognitive {A}nnotation",
author = {B{\"o}l{\"u}c{\"u}, Necva and
Can, Burcu},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.10/",
pages = "89--99",
abstract = "Universal Conceptual Cognitive Annotation (UCCA) (Abend and Rappoport, 2013a) is a cross-lingual semantic annotation framework that provides an easy annotation without any requirement for linguistic background. UCCA-annotated datasets have been already released in English, French, and German. In this paper, we introduce the first UCCA-annotated Turkish dataset that currently involves 50 sentences obtained from the METU-Sabanci Turkish Treebank (Atalay et al., 2003; Oflazeret al., 2003). We followed a semi-automatic annotation approach, where an external semantic parser is utilised for an initial annotation of the dataset, which is partially accurate and requires refinement. We manually revised the annotations obtained from the semantic parser that are not in line with the UCCA rules that we defined for Turkish. We used the same external semantic parser for evaluation purposes and conducted experiments with both zero-shot and few-shot learning. While the parser cannot predict remote edges in zero-shot setting, using even a small subset of training data in few-shot setting increased the overall F-1 score including the remote edges. This is the initial version of the annotated dataset and we are currently extending the dataset. We will release the current Turkish UCCA annotation guideline along with the annotated dataset."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bolucu-can-2022-turkish">
<titleInfo>
<title>Turkish Universal Conceptual Cognitive Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Necva</namePart>
<namePart type="family">Bölücü</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Universal Conceptual Cognitive Annotation (UCCA) (Abend and Rappoport, 2013a) is a cross-lingual semantic annotation framework that provides an easy annotation without any requirement for linguistic background. UCCA-annotated datasets have been already released in English, French, and German. In this paper, we introduce the first UCCA-annotated Turkish dataset that currently involves 50 sentences obtained from the METU-Sabanci Turkish Treebank (Atalay et al., 2003; Oflazeret al., 2003). We followed a semi-automatic annotation approach, where an external semantic parser is utilised for an initial annotation of the dataset, which is partially accurate and requires refinement. We manually revised the annotations obtained from the semantic parser that are not in line with the UCCA rules that we defined for Turkish. We used the same external semantic parser for evaluation purposes and conducted experiments with both zero-shot and few-shot learning. While the parser cannot predict remote edges in zero-shot setting, using even a small subset of training data in few-shot setting increased the overall F-1 score including the remote edges. This is the initial version of the annotated dataset and we are currently extending the dataset. We will release the current Turkish UCCA annotation guideline along with the annotated dataset.</abstract>
<identifier type="citekey">bolucu-can-2022-turkish</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.10/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>89</start>
<end>99</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Turkish Universal Conceptual Cognitive Annotation
%A Bölücü, Necva
%A Can, Burcu
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F bolucu-can-2022-turkish
%X Universal Conceptual Cognitive Annotation (UCCA) (Abend and Rappoport, 2013a) is a cross-lingual semantic annotation framework that provides an easy annotation without any requirement for linguistic background. UCCA-annotated datasets have been already released in English, French, and German. In this paper, we introduce the first UCCA-annotated Turkish dataset that currently involves 50 sentences obtained from the METU-Sabanci Turkish Treebank (Atalay et al., 2003; Oflazeret al., 2003). We followed a semi-automatic annotation approach, where an external semantic parser is utilised for an initial annotation of the dataset, which is partially accurate and requires refinement. We manually revised the annotations obtained from the semantic parser that are not in line with the UCCA rules that we defined for Turkish. We used the same external semantic parser for evaluation purposes and conducted experiments with both zero-shot and few-shot learning. While the parser cannot predict remote edges in zero-shot setting, using even a small subset of training data in few-shot setting increased the overall F-1 score including the remote edges. This is the initial version of the annotated dataset and we are currently extending the dataset. We will release the current Turkish UCCA annotation guideline along with the annotated dataset.
%U https://aclanthology.org/2022.lrec-1.10/
%P 89-99
Markdown (Informal)
[Turkish Universal Conceptual Cognitive Annotation](https://aclanthology.org/2022.lrec-1.10/) (Bölücü & Can, LREC 2022)
ACL