Banner: A Cost-Sensitive Contextualized Model for Bangla Named Entity Recognition

Abstract

Named Entity Recognition (NER) is a task in Natural Language Processing (NLP) that aims to classify words into a predetermined list of Named Entities (NE). Many architectures have produced good results on high resourced languages like English and Chinese. However, the NER task has not yet achieved much progress for Bangla, a low resource Language. In this paper, we perform the NER task on Bangla Language using Word2Vec and contextual Bidirectional Encoder Representations from Transformers (BERT) embeddings. We propose multiple BERT-based deep learning models that use the contextualized embedding from BERT as inputs and a simple statistical approach for class weight cost sensitive learning. The modified cost-sensitive loss function was used to address the class imbalance of the data. In our modified cost-sensitive loss function, we penalize the dominant classes by taking the ratio concerning the maximum sample in a class instead of the whole dataset. This penalty is made so that the learner learns slowly for the dominant class. In addition, we experiment by adding a Conditional Random Field (CRF) layer and incorporating Focal Loss to the training process. We found the best F1 Macro score to be 65.96%, F1 Micro score of 90.64%, and F1 Message Understanding Coreference (MUC) score of 72.04%, which were calculated at Named Entity level. Our experimental results demonstrate that one of the proposed models, which jointly optimizes for the CRF loss and class weighted cost-sensitive loss according to our proposed statistical approach, achieve an improvement of over 8% F1 MUC score on a recently introduced Bangla NER dataset when compared to previously published work.

B-NER: A Novel Bangla Named Entity Recognition Dataset With Largest Entities and Its Baseline Evaluation

“…Among recent studies, Karim et al used Densely Connected Network (DCN) in combination with Bidirectional Long Short Term Memory (BiLSTM). Ashrafi et al [45] implemented BERT-based deep neural architecture that uses the contextual embeddings from BERT [30] as input for multi-label classification. Table 1 illustrates a comprehensive overview of recent works on Bangla NER.…”

BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla

“…Many works have studied different Bangla NLU tasks in isolation, e.g., sentiment classification (Das and Bandyopadhyay, 2010;Sharfuddin et al, 2018;Tripto and Ali, 2018), semantic textual similarity (Shajalal and Aono, 2018), parts-of-speech (PoS) tagging (Alam et al, 2016), named entity recognition (NER) (Ashrafi et al, 2020). However, Bangla NLU has not yet had a comprehensive, unified study.…”

“…Joshi et al (2020b) categorized Bangla in the language group that lacks efforts in labeled data collection and relies on self-supervised pretraining (Devlin et al, 2019;Radford et al, 2019;Liu et al, 2019) to boost the natural language understanding (NLU) task performances. To date, the Bangla language has been continuing to rely on fine-tuning multilingual pretrained language models (PLMs) (Ashrafi et al, 2020;Das et al, 2021;Islam et al, 2021). However, since multilingual PLMs cover a wide range of languages (Conneau and Lample, 2019;, they are large (have hundreds of millions of parameters) and require substantial computational resources for fine-tuning.…”

Fusion Deep Learning and Machine Learning for Heterogeneous Military Entity Recognition

“…Furthermore, the entity type coverage was relatively small, and the effect of corpus set size on the experimental results and the effect of heterogeneous data on the experimental results were not illustrated in the experimental session. At present, entity recognition based on pretrained models and attention mechanism in the field of generic entity recognition is the mainstream [15][16][17][18][19][20], which gives important insight into the direction of entity recognition technology development in the military field.…”