@inproceedings{ali-etal-2020-siner,
title = "{S}i{NER}: A Large Dataset for {S}indhi Named Entity Recognition",
author = "Ali, Wazir and
Lu, Junyu and
Xu, Zenglin",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.361/",
pages = "2953--2961",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "We introduce the SiNER: a named entity recognition (NER) dataset for low-resourced Sindhi language with quality baselines. It contains 1,338 news articles and more than 1.35 million tokens collected from Kawish and Awami Awaz Sindhi newspapers using the begin-inside-outside (BIO) tagging scheme. The proposed dataset is likely to be a significant resource for statistical Sindhi language processing. The ultimate goal of developing SiNER is to present a gold-standard dataset for Sindhi NER along with quality baselines. We implement several baseline approaches of conditional random field (CRF) and recent popular state-of-the-art bi-directional long-short term memory (Bi-LSTM) models. The promising F1-score of 89.16 outputted by the Bi-LSTM-CRF model with character-level representations demonstrates the quality of our proposed SiNER dataset."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-etal-2020-siner">
<titleInfo>
<title>SiNER: A Large Dataset for Sindhi Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wazir</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zenglin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We introduce the SiNER: a named entity recognition (NER) dataset for low-resourced Sindhi language with quality baselines. It contains 1,338 news articles and more than 1.35 million tokens collected from Kawish and Awami Awaz Sindhi newspapers using the begin-inside-outside (BIO) tagging scheme. The proposed dataset is likely to be a significant resource for statistical Sindhi language processing. The ultimate goal of developing SiNER is to present a gold-standard dataset for Sindhi NER along with quality baselines. We implement several baseline approaches of conditional random field (CRF) and recent popular state-of-the-art bi-directional long-short term memory (Bi-LSTM) models. The promising F1-score of 89.16 outputted by the Bi-LSTM-CRF model with character-level representations demonstrates the quality of our proposed SiNER dataset.</abstract>
<identifier type="citekey">ali-etal-2020-siner</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.361/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2953</start>
<end>2961</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SiNER: A Large Dataset for Sindhi Named Entity Recognition
%A Ali, Wazir
%A Lu, Junyu
%A Xu, Zenglin
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F ali-etal-2020-siner
%X We introduce the SiNER: a named entity recognition (NER) dataset for low-resourced Sindhi language with quality baselines. It contains 1,338 news articles and more than 1.35 million tokens collected from Kawish and Awami Awaz Sindhi newspapers using the begin-inside-outside (BIO) tagging scheme. The proposed dataset is likely to be a significant resource for statistical Sindhi language processing. The ultimate goal of developing SiNER is to present a gold-standard dataset for Sindhi NER along with quality baselines. We implement several baseline approaches of conditional random field (CRF) and recent popular state-of-the-art bi-directional long-short term memory (Bi-LSTM) models. The promising F1-score of 89.16 outputted by the Bi-LSTM-CRF model with character-level representations demonstrates the quality of our proposed SiNER dataset.
%U https://aclanthology.org/2020.lrec-1.361/
%P 2953-2961
Markdown (Informal)
[SiNER: A Large Dataset for Sindhi Named Entity Recognition](https://aclanthology.org/2020.lrec-1.361/) (Ali et al., LREC 2020)
ACL