@inproceedings{taguchi-etal-2022-universal,
title = "{U}niversal {D}ependencies Treebank for {T}atar: Incorporating Intra-Word Code-Switching Information",
author = "Taguchi, Chihiro and
Iwata, Sei and
Watanabe, Taro",
editor = "Ojha, Atul Kr. and
Ahmadi, Sina and
Liu, Chao-Hong and
McCrae, John P.",
booktitle = "Proceedings of the Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.eurali-1.17",
pages = "95--104",
abstract = "This paper introduces a new Universal Dependencies treebank for the Tatar language named NMCTT. A significant feature of the corpus is that it includes code-switching (CS) information at a morpheme level, given the fact that Tatar texts contain intra-word CS between Tatar and Russian. We first outline NMCTT with a focus on differences from other treebanks of Turkic languages. Then, to evaluate the merit of the CS annotation, this study concisely reports the results of a language identification task implemented with Conditional Random Fields that considers POS tag information, which is readily available in treebanks in the CoNLL-U format. Experimenting on NMCTT and the Turkish-German CS treebank (SAGT), we demonstrate that the proposed annotation scheme introduced in NMCTT can improve the performance of the subword-level language identification. This annotation scheme for CS is not only universally applicable to languages with CS, but also shows a possibility to employ morphosyntactic information for CS-related downstream tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="taguchi-etal-2022-universal">
<titleInfo>
<title>Universal Dependencies Treebank for Tatar: Incorporating Intra-Word Code-Switching Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chihiro</namePart>
<namePart type="family">Taguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sei</namePart>
<namePart type="family">Iwata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</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 Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</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>This paper introduces a new Universal Dependencies treebank for the Tatar language named NMCTT. A significant feature of the corpus is that it includes code-switching (CS) information at a morpheme level, given the fact that Tatar texts contain intra-word CS between Tatar and Russian. We first outline NMCTT with a focus on differences from other treebanks of Turkic languages. Then, to evaluate the merit of the CS annotation, this study concisely reports the results of a language identification task implemented with Conditional Random Fields that considers POS tag information, which is readily available in treebanks in the CoNLL-U format. Experimenting on NMCTT and the Turkish-German CS treebank (SAGT), we demonstrate that the proposed annotation scheme introduced in NMCTT can improve the performance of the subword-level language identification. This annotation scheme for CS is not only universally applicable to languages with CS, but also shows a possibility to employ morphosyntactic information for CS-related downstream tasks.</abstract>
<identifier type="citekey">taguchi-etal-2022-universal</identifier>
<location>
<url>https://aclanthology.org/2022.eurali-1.17</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>95</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Universal Dependencies Treebank for Tatar: Incorporating Intra-Word Code-Switching Information
%A Taguchi, Chihiro
%A Iwata, Sei
%A Watanabe, Taro
%Y Ojha, Atul Kr.
%Y Ahmadi, Sina
%Y Liu, Chao-Hong
%Y McCrae, John P.
%S Proceedings of the Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F taguchi-etal-2022-universal
%X This paper introduces a new Universal Dependencies treebank for the Tatar language named NMCTT. A significant feature of the corpus is that it includes code-switching (CS) information at a morpheme level, given the fact that Tatar texts contain intra-word CS between Tatar and Russian. We first outline NMCTT with a focus on differences from other treebanks of Turkic languages. Then, to evaluate the merit of the CS annotation, this study concisely reports the results of a language identification task implemented with Conditional Random Fields that considers POS tag information, which is readily available in treebanks in the CoNLL-U format. Experimenting on NMCTT and the Turkish-German CS treebank (SAGT), we demonstrate that the proposed annotation scheme introduced in NMCTT can improve the performance of the subword-level language identification. This annotation scheme for CS is not only universally applicable to languages with CS, but also shows a possibility to employ morphosyntactic information for CS-related downstream tasks.
%U https://aclanthology.org/2022.eurali-1.17
%P 95-104
Markdown (Informal)
[Universal Dependencies Treebank for Tatar: Incorporating Intra-Word Code-Switching Information](https://aclanthology.org/2022.eurali-1.17) (Taguchi et al., EURALI 2022)
ACL