@inproceedings{shavarani-sekine-2020-multi,
title = "Multi-class Multilingual Classification of {W}ikipedia Articles Using Extended Named Entity Tag Set",
author = "Shavarani, Hassan S. and
Sekine, Satoshi",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.150",
pages = "1197--1201",
abstract = "Wikipedia is a great source of general world knowledge which can guide NLP models better understand their motivation to make predictions. Structuring Wikipedia is the initial step towards this goal which can facilitate fine-grain classification of articles. In this work, we introduce the Shinra 5-Language Categorization Dataset (SHINRA-5LDS), a large multi-lingual and multi-labeled set of annotated Wikipedia articles in Japanese, English, French, German, and Farsi using Extended Named Entity (ENE) tag set. We evaluate the dataset using the best models provided for ENE label set classification and show that the currently available classification models struggle with large datasets using fine-grained tag sets.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shavarani-sekine-2020-multi">
<titleInfo>
<title>Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Shavarani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Sekine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Wikipedia is a great source of general world knowledge which can guide NLP models better understand their motivation to make predictions. Structuring Wikipedia is the initial step towards this goal which can facilitate fine-grain classification of articles. In this work, we introduce the Shinra 5-Language Categorization Dataset (SHINRA-5LDS), a large multi-lingual and multi-labeled set of annotated Wikipedia articles in Japanese, English, French, German, and Farsi using Extended Named Entity (ENE) tag set. We evaluate the dataset using the best models provided for ENE label set classification and show that the currently available classification models struggle with large datasets using fine-grained tag sets.</abstract>
<identifier type="citekey">shavarani-sekine-2020-multi</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.150</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>1197</start>
<end>1201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set
%A Shavarani, Hassan S.
%A Sekine, Satoshi
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F shavarani-sekine-2020-multi
%X Wikipedia is a great source of general world knowledge which can guide NLP models better understand their motivation to make predictions. Structuring Wikipedia is the initial step towards this goal which can facilitate fine-grain classification of articles. In this work, we introduce the Shinra 5-Language Categorization Dataset (SHINRA-5LDS), a large multi-lingual and multi-labeled set of annotated Wikipedia articles in Japanese, English, French, German, and Farsi using Extended Named Entity (ENE) tag set. We evaluate the dataset using the best models provided for ENE label set classification and show that the currently available classification models struggle with large datasets using fine-grained tag sets.
%U https://aclanthology.org/2020.lrec-1.150
%P 1197-1201
Markdown (Informal)
[Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set](https://aclanthology.org/2020.lrec-1.150) (Shavarani & Sekine, LREC 2020)
ACL