Improved Deep Persian Named Entity Recognition

Bokaei, Mohammad Hadi; Mahmoudi, Maryam Tayefeh

doi:10.1109/istel.2018.8661067

Cited by 8 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, due to a low tag count of Time and resemblance to Date make BERT-PersNER acts worst on Time. Table 3 shows BERT-PersNER performance against two recent studies (Shahshahani et al, 2019;Bokaei and Mahmoudi, 2018). As it is observed, our proposed model outperforms the baselines on Arman.…”

Section: Methodsmentioning

confidence: 76%

“…For the first component, Word2Vec (Mikolov et al, 2013) was used in (Lample et al, 2016) and both Word2Vec and GloVe (Pennington et al, 2014) were used in (Poost-chi et al, 2018). As the second component, in most studies, a bidirectional long short-term memory (BiLSTM) has been used to capture long-distance dependencies (Li et al, 2020;Shahshahani et al, 2019;Lample et al, 2016;Bokaei and Mahmoudi, 2018;Poostchi et al, 2018). In other studies, an architecture named Transformer (Vaswani et al, 2017) was used.…”

Section: Named Entity Recognitionmentioning

confidence: 99%

“…As the last component, Conditional Random Field (CRF) (Lafferty et al, 2001) has been mostly used as the referred tag decoder. The main reason for choosing CRF is that, instead of merely looking for the best label (tag) for each word, it jointly uses neighboring tags to determine a sequence of output labels (Li et al, 2020;Lample et al, 2016;Bokaei and Mahmoudi, 2018;Poostchi et al, 2018;Taher et al, 2019). (Poostchi et al, 2018;Shahshahani et al, 2019).…”

Section: Named Entity Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

BERT-PersNER: a New Model for Persian Named Entity Recognition

Farahani¹,

Ghassem-Sani

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Me

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 76%

Section: Named Entity Recognitionmentioning

confidence: 99%

Section: Named Entity Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

BERT-PersNER: a New Model for Persian Named Entity Recognition

Farahani¹,

Ghassem-Sani

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Me

View full text Add to dashboard Cite

“…Another approach for Persian NER is provided by [33] which combines a rule-based grammatical approach. Moreover, a Deep Learning approach for Persian NER is provided in [34] facilitating bidirectional LSTM networks. Beheshti-NER [35] uses multilingual Google BERT to form a fine-tuned model for Persian NER and is the closest work to present work.…”

Section: Nlp Downstream Tasksmentioning

confidence: 99%

ParsBERT: Transformer-based Model for Persian Language Understanding

Farahani

Gharachorloo

Farahani

et al. 2021

Neural Process Lett

107

View full text Add to dashboard Cite

The surge of pre-trained language models has begun a new era in the field of Natural Language Processing (NLP) by allowing us to build powerful language models. Among these models, Transformer-based models such as BERT have become increasingly popular due to their stateof-the-art performance. However, these models are usually focused on English, leaving other languages to multilingual models with limited resources. This paper proposes a monolingual BERT for the Persian language (ParsBERT), which shows its state-of-the-art performance compared to other architectures and multilingual models. Also, since the amount of data available for NLP tasks in Persian is very restricted, a massive dataset for different NLP tasks as well as pre-training the model is composed. ParsBERT obtains higher scores in all datasets, including existing ones and gathered ones, and improves the state-of-the-art performance by outperforming both multilingual BERT and other prior works in Sentiment Analysis, Text Classification, and Named Entity Recognition tasks.

show abstract

“…Another approach for Persian NER is provided by [33] which combines a rulebased grammatical approach. Moreover, a Deep Learning approach for Persian NER is provided in [34] facilitating bidirectional LSTM networks. Beheshti-NER [35] uses multilingual Google BERT to form a fine-tuned model for Persian NER and is the closest work to present work.…”

Section: Nlp Downstream Tasksmentioning

confidence: 99%

ParsBERT: Transformer-based Model for Persian Language Understanding

Farahani,

Gharachorloo,

Farahani

et al. 2020

Preprint

View full text Add to dashboard Cite

The surge of pre-trained language models has begun a new era in the field of Natural Language Processing (NLP) by allowing us to build powerful language models. Among these models, Transformer-based models such as BERT have become increasingly popular due to their state-of-the-art performance. However, these models are usually focused on English, leaving other languages to multilingual models with limited resources. This paper proposes a monolingual BERT for the Persian language (ParsBERT), which shows its state-ofthe-art performance compared to other architectures and multilingual models. Also, since the amount of data available for NLP tasks in Persian is very restricted, a massive dataset for different NLP tasks as well as pretraining the model is composed. ParsBERT obtains higher scores in all datasets, including existing ones as well as composed ones and improves the state-of-the-art performance by outperforming both multilingual BERT and other prior works in Sentiment Analysis, Text Classification and Named Entity Recognition tasks.

show abstract

Improved Deep Persian Named Entity Recognition

Cited by 8 publications

References 13 publications

BERT-PersNER: a New Model for Persian Named Entity Recognition

BERT-PersNER: a New Model for Persian Named Entity Recognition

ParsBERT: Transformer-based Model for Persian Language Understanding

ParsBERT: Transformer-based Model for Persian Language Understanding

Contact Info

Product

Resources

About