Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks
The vast amount of unstructured data spread on a daily basis rises the need for developing effective information retrieval and extraction methods. Named Entity Recognition is a challenging classification task for structuring data into pre-defined labels, and is even more complicated when being appli...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8993806/ |
| id |
doaj-7e9258e90bbc481fbd8c1f59f91e90ef |
|---|---|
| record_format |
Article |
| spelling |
doaj-7e9258e90bbc481fbd8c1f59f91e90ef2021-03-30T02:40:53ZengIEEEIEEE Access2169-35362020-01-018377363774510.1109/ACCESS.2020.29733198993806Transfer Learning for Arabic Named Entity Recognition With Deep Neural NetworksMohammad Al-Smadi0https://orcid.org/0000-0002-7808-6962Saad Al-Zboon1https://orcid.org/0000-0003-2367-5943Yaser Jararweh2https://orcid.org/0000-0002-4403-3846Patrick Juola3https://orcid.org/0000-0003-2578-6233Computer Science Department, Jordan University of Science and Technology, Irbid, JordanComputer Science Department, Jordan University of Science and Technology, Irbid, JordanComputer Science Department, Jordan University of Science and Technology, Irbid, JordanMathematics and Computer Science Department, Duquesne University, Pittsburgh, PA, USAThe vast amount of unstructured data spread on a daily basis rises the need for developing effective information retrieval and extraction methods. Named Entity Recognition is a challenging classification task for structuring data into pre-defined labels, and is even more complicated when being applied on the Arabic language due to its special traits and complex nature. This article presents a novel Deep Learning approach for Standard Arabic Named Entity Recognition that proved its out-performance when being compared to previous works. The main aim of building a new model is to provide better fine-grained results for use in the Natural Language Processing fields. In our proposed methodology we utilized transfer learning with deep neural networks to build a Pooled-GRU model combined with the Multilingual Universal Sentence Encoder. Our proposed model scored about 17% enhancement when being compared to previous work.https://ieeexplore.ieee.org/document/8993806/Natural language processingdeep learningtransfer learningANERuniversal sentence encoderBi-LSTM |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Mohammad Al-Smadi Saad Al-Zboon Yaser Jararweh Patrick Juola |
| spellingShingle |
Mohammad Al-Smadi Saad Al-Zboon Yaser Jararweh Patrick Juola Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks IEEE Access Natural language processing deep learning transfer learning ANER universal sentence encoder Bi-LSTM |
| author_facet |
Mohammad Al-Smadi Saad Al-Zboon Yaser Jararweh Patrick Juola |
| author_sort |
Mohammad Al-Smadi |
| title |
Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks |
| title_short |
Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks |
| title_full |
Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks |
| title_fullStr |
Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks |
| title_full_unstemmed |
Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks |
| title_sort |
transfer learning for arabic named entity recognition with deep neural networks |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2020-01-01 |
| description |
The vast amount of unstructured data spread on a daily basis rises the need for developing effective information retrieval and extraction methods. Named Entity Recognition is a challenging classification task for structuring data into pre-defined labels, and is even more complicated when being applied on the Arabic language due to its special traits and complex nature. This article presents a novel Deep Learning approach for Standard Arabic Named Entity Recognition that proved its out-performance when being compared to previous works. The main aim of building a new model is to provide better fine-grained results for use in the Natural Language Processing fields. In our proposed methodology we utilized transfer learning with deep neural networks to build a Pooled-GRU model combined with the Multilingual Universal Sentence Encoder. Our proposed model scored about 17% enhancement when being compared to previous work. |
| topic |
Natural language processing deep learning transfer learning ANER universal sentence encoder Bi-LSTM |
| url |
https://ieeexplore.ieee.org/document/8993806/ |
| work_keys_str_mv |
AT mohammadalsmadi transferlearningforarabicnamedentityrecognitionwithdeepneuralnetworks AT saadalzboon transferlearningforarabicnamedentityrecognitionwithdeepneuralnetworks AT yaserjararweh transferlearningforarabicnamedentityrecognitionwithdeepneuralnetworks AT patrickjuola transferlearningforarabicnamedentityrecognitionwithdeepneuralnetworks |
| _version_ |
1724184747010162688 |