Arabic Named Entity Recognition: What Works and What’s Next

Liu, Liyuan; Shang, Jingbo

doi:10.18653/v1/w19-4607

Cited by 15 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, as we have shown, most recent corpora and tasks of Arabic NER have tagged tokens, without any explicit mentioned of morphemes, and results on them are much lower than on English. In addition, neural architectures for Arabic NER have excluded morphological information for far (Khalifa and Shaalan, 2019;Liu et al, 2019). We hypothesise that explicit modeling of morphology as proposed herein will improve performance on neural Arabic NER as well.…”

Section: Modeling Sub-word Units For Morphologymentioning

confidence: 97%

Neural Modeling for Named Entities and Morphology (NEMO2)

Bareket

Tsarfaty

2021

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens. Morphologically rich languages (MRLs) pose a challenge to this basic formulation, as the boundaries of named entities do not necessarily coincide with token boundaries, rather, they respect morphological boundaries. To address NER in MRLs we then need to answer two fundamental questions, namely, what are the basic units to be labeled, and how can these units be detected and classified in realistic settings (i.e., where no gold morphology is available). We empirically investigate these questions on a novel NER benchmark, with parallel token- level and morpheme-level NER annotations, which we develop for Modern Hebrew, a morphologically rich-and-ambiguous language. Our results show that explicitly modeling morphological boundaries leads to improved NER performance, and that a novel hybrid architecture, in which NER precedes and prunes morphological decomposition, greatly outperforms the standard pipeline, where morphological decomposition strictly precedes NER, setting a new performance bar for both Hebrew NER and Hebrew morphological decomposition tasks.

show abstract

Section: Modeling Sub-word Units For Morphologymentioning

confidence: 97%

Neural Modeling for Named Entities and Morphology (NEMO2)

Bareket

Tsarfaty

2021

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Type Title [8] 2009 Report NERA: Named entity recognition for Arabic [9] 2014 Survey A survey of Arabic named entity recognition and classification [10] 2015 Report Named entity recognition for arabic social media [11] 2016 Survey Arabic named entity recognition -a survey and analysis [12] 2017 Survey A comparative review of machine learning for Arabic named entity recognition [13] 2019 Report Arabic named entity recognition using deep learning approach [14] 2019 Report Arabic named entity recognition: What works and what's next [15] 2020 Survey A recent survey of arabic named entity recognition on social media.…”

Section: Cite Yearmentioning

confidence: 99%

A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trends

Qu¹,

Gu²,

Xia³

et al. 2023

Preprint

View full text Add to dashboard Cite

As more and more Arabic texts emerged on the Internet, extracting important information from these Arabic texts is especially useful. As a fundamental technology, Named entity recognition (NER) serves as the core component in information extraction technology, while also playing a critical role in many other Natural Language Processing (NLP) systems, such as question answering and knowledge graph building. In this paper, we provide a comprehensive review of the development of Arabic NER, especially the recent advances in deep learning and pre-trained language model. Specifically, we first introduce the background of Arabic NER, including the characteristics of Arabic and existing resources for Arabic NER. Then, we systematically review the development of Arabic NER methods. Traditional Arabic NER systems focus on feature engineering and designing domain-specific rules. In recent years, deep learning methods achieve significant progress by representing texts via continuous vector representations. With the growth of pre-trained language model, Arabic NER yields better performance. Finally, we conclude the method gap between Arabic NER and NER methods from other languages, which helps outline future directions for Arabic NER.

show abstract

“…However, applying models trained on MSA text to social media (mostly dialectal) text has led to unsatisfactory results [57]. Recent contextualized embeddings and other deep learning approaches such as sequence to sequence models and convolutional neural networks have led to improved results for Arabic NER [28,109,117,136]. It is expected that the use of contextualized embeddings trained on larger corpora of varying Arabic dialects, coupled with the use of deep learning models is likely to contribute positively to Arabic NER.…”

Section: Named Entity Recognitionmentioning

confidence: 99%