AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations

Toqeer Ehsan; Amjad Ali; Ala Al-Fuqaha

AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations

Toqeer Ehsan
, Amjad Ali
, Ala Al-Fuqaha

Not published at VTT

University of Gujrat

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

This paper presents Arabic named entity recognition models by employing single-task and multi-task learning paradigms. The models were developed by using character-based contextualized Embeddings from Language Model (ELMo) in the input layers of the Bidirectional Long-Short Term Memory (BiLSTM) networks. The ELMo embeddings are quite capable of learning the morphology and contextual information of tokens in word sequences. The single-task learning model outperformed the multi-task learning model, achieving micro F1-scores of 0.8751 and 0.8884, respectively, ranking 10th and 7th in the shared task for flat and nested NER.

Original language	English
Title of host publication	Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023)
Publisher	Association for Computational Linguistics (ACL)
Pages	783-788
Number of pages	6
ISBN (Electronic)	978-1-959429-27-2
Publication status	Published - 2023
MoE publication type	A4 Article in a conference publication

Access to Document

https://aclanthology.org/2023.arabicnlp-1.pdf

Cite this

Ehsan, T., Ali, A., & Al-Fuqaha, A. (2023). AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations. In Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023) (pp. 783-788). Association for Computational Linguistics (ACL). https://aclanthology.org/2023.arabicnlp-1.pdf

@inproceedings{ddb711e47cb249b99c618db64fce7ac8,

title = "AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations",

abstract = "This paper presents Arabic named entity recognition models by employing single-task and multi-task learning paradigms. The models were developed by using character-based contextualized Embeddings from Language Model (ELMo) in the input layers of the Bidirectional Long-Short Term Memory (BiLSTM) networks. The ELMo embeddings are quite capable of learning the morphology and contextual information of tokens in word sequences. The single-task learning model outperformed the multi-task learning model, achieving micro F1-scores of 0.8751 and 0.8884, respectively, ranking 10th and 7th in the shared task for flat and nested NER.",

author = "Toqeer Ehsan and Amjad Ali and Ala Al-Fuqaha",

year = "2023",

language = "English",

pages = "783--788",

booktitle = "Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023)",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

}

Ehsan, T, Ali, A & Al-Fuqaha, A 2023, AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations. in Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023). Association for Computational Linguistics (ACL), pp. 783-788. <https://aclanthology.org/2023.arabicnlp-1.pdf>

AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations. / Ehsan, Toqeer; Ali, Amjad; Al-Fuqaha, Ala.
Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023). Association for Computational Linguistics (ACL), 2023. p. 783-788.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations

AU - Ehsan, Toqeer

AU - Ali, Amjad

AU - Al-Fuqaha, Ala

PY - 2023

Y1 - 2023

N2 - This paper presents Arabic named entity recognition models by employing single-task and multi-task learning paradigms. The models were developed by using character-based contextualized Embeddings from Language Model (ELMo) in the input layers of the Bidirectional Long-Short Term Memory (BiLSTM) networks. The ELMo embeddings are quite capable of learning the morphology and contextual information of tokens in word sequences. The single-task learning model outperformed the multi-task learning model, achieving micro F1-scores of 0.8751 and 0.8884, respectively, ranking 10th and 7th in the shared task for flat and nested NER.

AB - This paper presents Arabic named entity recognition models by employing single-task and multi-task learning paradigms. The models were developed by using character-based contextualized Embeddings from Language Model (ELMo) in the input layers of the Bidirectional Long-Short Term Memory (BiLSTM) networks. The ELMo embeddings are quite capable of learning the morphology and contextual information of tokens in word sequences. The single-task learning model outperformed the multi-task learning model, achieving micro F1-scores of 0.8751 and 0.8884, respectively, ranking 10th and 7th in the shared task for flat and nested NER.

M3 - Conference article in proceedings

SP - 783

EP - 788

BT - Proceedings of the The First Arabic Natural Language Processing Conference (ArabicNLP 2023)

PB - Association for Computational Linguistics (ACL)

ER -

AlphaBrains at WojoodNER shared task: Arabic Named Entity Recognition by Using Character-based Context-Sensitive Word Representations

Abstract

Access to Document

Fingerprint

Cite this