@inproceedings{hatab-etal-2022-enhancing,
title = "Enhancing Deep Learning with Embedded Features for {A}rabic Named Entity Recognition",
author = "Hatab, Ali L. and
Sabty, Caroline and
Abdennadher, Slim",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.524",
pages = "4904--4912",
abstract = "The introduction of word embedding models has remarkably changed many Natural Language Processing tasks. Word embeddings can automatically capture the semantics of words and other hidden features. Nonetheless, the Arabic language is highly complex, which results in the loss of important information. This paper uses Madamira, an external knowledge source, to generate additional word features. We evaluate the utility of adding these features to conventional word and character embeddings to perform the Named Entity Recognition (NER) task on Modern Standard Arabic (MSA). Our NER model is implemented using Bidirectional Long Short Term Memory and Conditional Random Fields (BiLSTM-CRF). We add morphological and syntactical features to different word embeddings to train the model. The added features improve the performance by different values depending on the used embedding model. The best performance is achieved by using Bert embeddings. Moreover, our best model outperforms the previous systems to the best of our knowledge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hatab-etal-2022-enhancing">
<titleInfo>
<title>Enhancing Deep Learning with Embedded Features for Arabic Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Hatab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Sabty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slim</namePart>
<namePart type="family">Abdennadher</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 Thirteenth 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">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>
</relatedItem>
<abstract>The introduction of word embedding models has remarkably changed many Natural Language Processing tasks. Word embeddings can automatically capture the semantics of words and other hidden features. Nonetheless, the Arabic language is highly complex, which results in the loss of important information. This paper uses Madamira, an external knowledge source, to generate additional word features. We evaluate the utility of adding these features to conventional word and character embeddings to perform the Named Entity Recognition (NER) task on Modern Standard Arabic (MSA). Our NER model is implemented using Bidirectional Long Short Term Memory and Conditional Random Fields (BiLSTM-CRF). We add morphological and syntactical features to different word embeddings to train the model. The added features improve the performance by different values depending on the used embedding model. The best performance is achieved by using Bert embeddings. Moreover, our best model outperforms the previous systems to the best of our knowledge.</abstract>
<identifier type="citekey">hatab-etal-2022-enhancing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.524</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4904</start>
<end>4912</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Deep Learning with Embedded Features for Arabic Named Entity Recognition
%A Hatab, Ali L.
%A Sabty, Caroline
%A Abdennadher, Slim
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F hatab-etal-2022-enhancing
%X The introduction of word embedding models has remarkably changed many Natural Language Processing tasks. Word embeddings can automatically capture the semantics of words and other hidden features. Nonetheless, the Arabic language is highly complex, which results in the loss of important information. This paper uses Madamira, an external knowledge source, to generate additional word features. We evaluate the utility of adding these features to conventional word and character embeddings to perform the Named Entity Recognition (NER) task on Modern Standard Arabic (MSA). Our NER model is implemented using Bidirectional Long Short Term Memory and Conditional Random Fields (BiLSTM-CRF). We add morphological and syntactical features to different word embeddings to train the model. The added features improve the performance by different values depending on the used embedding model. The best performance is achieved by using Bert embeddings. Moreover, our best model outperforms the previous systems to the best of our knowledge.
%U https://aclanthology.org/2022.lrec-1.524
%P 4904-4912
Markdown (Informal)
[Enhancing Deep Learning with Embedded Features for Arabic Named Entity Recognition](https://aclanthology.org/2022.lrec-1.524) (Hatab et al., LREC 2022)
ACL