@inproceedings{kardinata-etal-2024-constructing,
title = "Constructing {I}ndonesian-{E}nglish Travelogue Dataset",
author = "Kardinata, Eunike Andriani and
Ouchi, Hiroki and
Watanabe, Taro",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.333",
pages = "3759--3771",
abstract = "Research in low-resource language is often hampered due to the under-representation of how the language is being used in reality. This is particularly true for Indonesian language because there is a limited variety of textual datasets, and majority were acquired from official sources with formal writing style. All the more for the task of geoparsing, which could be implemented for navigation and travel planning applications, such datasets are rare, even in the high-resource languages, such as English. Being aware of the need for a new resource in both languages for this specific task, we constructed a new dataset comprising both Indonesian and English from personal travelogue articles. Our dataset consists of 88 articles, exactly half of them written in each language. We covered both named and nominal expressions of four entity types related to travel: location, facility, transportation, and line. We also conducted experiments by training classifiers to recognise named entities and their nominal expressions. The results of our experiments showed a promising future use of our dataset as we obtained F1-score above 0.9 for both languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kardinata-etal-2024-constructing">
<titleInfo>
<title>Constructing Indonesian-English Travelogue Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunike</namePart>
<namePart type="given">Andriani</namePart>
<namePart type="family">Kardinata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Ouchi</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>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Research in low-resource language is often hampered due to the under-representation of how the language is being used in reality. This is particularly true for Indonesian language because there is a limited variety of textual datasets, and majority were acquired from official sources with formal writing style. All the more for the task of geoparsing, which could be implemented for navigation and travel planning applications, such datasets are rare, even in the high-resource languages, such as English. Being aware of the need for a new resource in both languages for this specific task, we constructed a new dataset comprising both Indonesian and English from personal travelogue articles. Our dataset consists of 88 articles, exactly half of them written in each language. We covered both named and nominal expressions of four entity types related to travel: location, facility, transportation, and line. We also conducted experiments by training classifiers to recognise named entities and their nominal expressions. The results of our experiments showed a promising future use of our dataset as we obtained F1-score above 0.9 for both languages.</abstract>
<identifier type="citekey">kardinata-etal-2024-constructing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.333</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3759</start>
<end>3771</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing Indonesian-English Travelogue Dataset
%A Kardinata, Eunike Andriani
%A Ouchi, Hiroki
%A Watanabe, Taro
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kardinata-etal-2024-constructing
%X Research in low-resource language is often hampered due to the under-representation of how the language is being used in reality. This is particularly true for Indonesian language because there is a limited variety of textual datasets, and majority were acquired from official sources with formal writing style. All the more for the task of geoparsing, which could be implemented for navigation and travel planning applications, such datasets are rare, even in the high-resource languages, such as English. Being aware of the need for a new resource in both languages for this specific task, we constructed a new dataset comprising both Indonesian and English from personal travelogue articles. Our dataset consists of 88 articles, exactly half of them written in each language. We covered both named and nominal expressions of four entity types related to travel: location, facility, transportation, and line. We also conducted experiments by training classifiers to recognise named entities and their nominal expressions. The results of our experiments showed a promising future use of our dataset as we obtained F1-score above 0.9 for both languages.
%U https://aclanthology.org/2024.lrec-main.333
%P 3759-3771
Markdown (Informal)
[Constructing Indonesian-English Travelogue Dataset](https://aclanthology.org/2024.lrec-main.333) (Kardinata et al., LREC-COLING 2024)
ACL
- Eunike Andriani Kardinata, Hiroki Ouchi, and Taro Watanabe. 2024. Constructing Indonesian-English Travelogue Dataset. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3759–3771, Torino, Italia. ELRA and ICCL.