@inproceedings{touileb-2022-nerdz,
title = "{NERD}z: A Preliminary Dataset of Named Entities for {A}lgerian",
author = "Touileb, Samia",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.13",
pages = "95--101",
abstract = "This paper introduces a first step towards creating the NERDz dataset. A manually annotated dataset of named entities for the Algerian vernacular dialect. The annotations are built on top of a recent extension to the Algerian NArabizi Treebank, comprizing NArabizi sentences with manual transliterations into Arabic and code-switched scripts. NERDz is therefore not only the first dataset of named entities for Algerian, but it also comprises parallel entities written in Latin, Arabic, and code-switched scripts. We present a detailed overview of our annotations, inter-annotator agreement measures, and define two preliminary baselines using a neural sequence labeling approach and an Algerian BERT model. We also make the annotation guidelines and the annotations available for future work",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="touileb-2022-nerdz">
<titleInfo>
<title>NERDz: A Preliminary Dataset of Named Entities for Algerian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a first step towards creating the NERDz dataset. A manually annotated dataset of named entities for the Algerian vernacular dialect. The annotations are built on top of a recent extension to the Algerian NArabizi Treebank, comprizing NArabizi sentences with manual transliterations into Arabic and code-switched scripts. NERDz is therefore not only the first dataset of named entities for Algerian, but it also comprises parallel entities written in Latin, Arabic, and code-switched scripts. We present a detailed overview of our annotations, inter-annotator agreement measures, and define two preliminary baselines using a neural sequence labeling approach and an Algerian BERT model. We also make the annotation guidelines and the annotations available for future work</abstract>
<identifier type="citekey">touileb-2022-nerdz</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.13</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>95</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NERDz: A Preliminary Dataset of Named Entities for Algerian
%A Touileb, Samia
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F touileb-2022-nerdz
%X This paper introduces a first step towards creating the NERDz dataset. A manually annotated dataset of named entities for the Algerian vernacular dialect. The annotations are built on top of a recent extension to the Algerian NArabizi Treebank, comprizing NArabizi sentences with manual transliterations into Arabic and code-switched scripts. NERDz is therefore not only the first dataset of named entities for Algerian, but it also comprises parallel entities written in Latin, Arabic, and code-switched scripts. We present a detailed overview of our annotations, inter-annotator agreement measures, and define two preliminary baselines using a neural sequence labeling approach and an Algerian BERT model. We also make the annotation guidelines and the annotations available for future work
%U https://aclanthology.org/2022.aacl-short.13
%P 95-101
Markdown (Informal)
[NERDz: A Preliminary Dataset of Named Entities for Algerian](https://aclanthology.org/2022.aacl-short.13) (Touileb, AACL-IJCNLP 2022)
ACL
- Samia Touileb. 2022. NERDz: A Preliminary Dataset of Named Entities for Algerian. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 95–101, Online only. Association for Computational Linguistics.