Bengali text document categorization based on very deep convolution neural network

Hossain, Md. Rajib; Hoque, Mohammed Moshiul; Siddique, Nazmul; Sarker, Iqbal H.

doi:10.1016/j.eswa.2021.115394

Cited by 35 publications

(12 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e model of neural network CNN [12,13] or BiLSTM [9,10] combined with CRF is based on the recognition model after word segmentation, and then, word2vec is used for word vector representation. To improve the effect of entity recognition, some scholars [24,25] use semantic information to improve the word vector as a result.…”

Section: Character-based Methodsmentioning

confidence: 99%

“…It shows that the BiLSTM method is superior to the CRF baseline model in different granularity legal domain corpora. Yin et al [11] proposed a method of judicial named entity recognition combining CNN and [12,13] LSTM. First, word embedding and CNN are used to obtain character-level embedding representation, and then, BiLSTM is used as an encoder, and one-way LSTM and character-level CNN are used as a decoder.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Named Entity Recognition for Public Interest Litigation Based on a Deep Contextualized Pretraining Approach

Dong

Kong

Wen-lian

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

The named entity recognition (NER) in the field of public interest litigation can assist prosecutors in handling cases and provide them with specific entities in making legal documents. Previously, the context-free deep learning model is used to catch the semantic comprehension, in which the static word vector is obtained without considering the context. Moreover, this kind of method relies on word segmentation technology and cannot solve the error transmission caused by word segmentation inaccuracy, which brings great challenges to the Chinese NER task. To tackle the above issues, an entity recognition method based on pretraining is proposed. First, based on the basic entities, three legal ontologies, NERP, NERCGP, and NERFPP are developed to expand the named entity recognition corpus in the judicial field. Second, a variant of the pretrained model BERT (Bidirectional Encoder Representations from Transformer) called BERT-WWM (whole-word mask)-EXT(extra) is introduced to catch the text character-level word vector hierarchical and the context bidirectional features, which effectively solve the problem of task boundary division of named entities. Then, to further improve the model recognition effect, the general knowledge learned from the pretrained model is used to fit the downstream neural network BiLSTM (bi-long short-term memory), and at the end of the architecture, CRF (conditional random fields) is introduced to restrict the label relationship. Finally, the experimental results show that the proposed method is more effective than the existing methods, which reach 96% and 90% in the F1 index of NER and NERP entities, respectively.

show abstract

Section: Character-based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Named Entity Recognition for Public Interest Litigation Based on a Deep Contextualized Pretraining Approach

Dong

Kong

Wen-lian

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Despite the limited amount of the data, Hossain et al [24] discovered that text-graph convolutional neural (GCN) accomplished better than GRU-LSTM, BiLSTM, Char-CNN, LSTM, and bidirectional encoder representations from transformers (BERT) in classifying online Bangla news. As so far, there is a scarcity of standard data set in the Bangla language, so a data set have been prepared by scraping the news articles from various electronic news sites such as 'https://www.prothomalo.com/'.…”

Section: Data Collectionmentioning

confidence: 99%

Comparison analysis of Bangla news articles classification using support vector machine and logistic regression

et al. 2023

View full text Add to dashboard Cite

In the information age, Bangla news articles on the internet are fast-growing. For organizing, every news site has a particular structure and categorization. News article classification is a method to determine a document's classification based on various predefined categories. This research discusses the classification of Bangla news articles on the online platform and tries to make constructive comparison using several classification algorithms. For Bangla news articles classification, term frequencyinverse document frequency (TF-IDF) weighting and count vectorizer have been used as a feature extraction process, and two common classifiers named support vector machine (SVM) and logistic regression (LR) employed for classifying the documents. It is clear that the accuracy of the experimental results by applying SVM is 84.0% and LR is 81.0% for twelve categories of news articles. In this research work, when we have made comparison two renowned classification algorithms applied on the Bangla news articles, LR was outperformed by SVM.

show abstract

“…Sarcasm detection on different low resource languages like Indonesian [6] , Hindi [7] , Czech [8] , Japanese [9] are available. Nonetheless, despite being the world's seventh most spoken language, with 240 million native speakers [10] , research on sarcasm detection in Bengali is underdeveloped and underutilized. Identifying sarcasm from Bengali text is currently a difficult task for NLP researchers due to limited resources and a paucity of large-scale sarcasm data.…”

Section: Introductionmentioning

confidence: 99%

A transformer-based generative adversarial learning to detect sarcasm from Bengali text with correct classification of confusing text

Lora,

Jahan,

Hussain

et al. 2023

Heliyon

View full text Add to dashboard Cite

Bengali text document categorization based on very deep convolution neural network

Cited by 35 publications

References 76 publications

Named Entity Recognition for Public Interest Litigation Based on a Deep Contextualized Pretraining Approach

Named Entity Recognition for Public Interest Litigation Based on a Deep Contextualized Pretraining Approach

Comparison analysis of Bangla news articles classification using support vector machine and logistic regression

A transformer-based generative adversarial learning to detect sarcasm from Bengali text with correct classification of confusing text

Contact Info

Product

Resources

About