Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network
This work addresses the problem of limited NLP resources for Bengali speakers, offering benchmarks and embeddings to improve tasks like hate speech detection, but it is incremental as it applies existing methods to a new language.
The paper tackles the lack of computational resources for NLP tasks in under-resourced languages like Bengali by providing classification benchmarks for hate speech detection, document classification, and sentiment analysis, achieving F1-scores of up to 92.30%, 82.25%, and 90.45% respectively using a Multichannel Convolutional-LSTM network with BengFastText embeddings.
Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices but also enables people to express anti-social behaviour like online harassment, cyberbullying, and hate speech. Numerous works have been proposed to utilize these data for social and anti-social behaviours analysis, document characterization, and sentiment analysis by predicting the contexts mostly for highly resourced languages such as English. However, there are languages that are under-resources, e.g., South Asian languages like Bengali, Tamil, Assamese, Telugu that lack of computational resources for the NLP tasks. In this paper, we provide several classification benchmarks for Bengali, an under-resourced language. We prepared three datasets of expressing hate, commonly used topics, and opinions for hate speech detection, document classification, and sentiment analysis, respectively. We built the largest Bengali word embedding models to date based on 250 million articles, which we call BengFastText. We perform three different experiments, covering document classification, sentiment analysis, and hate speech detection. We incorporate word embeddings into a Multichannel Convolutional-LSTM (MConv-LSTM) network for predicting different types of hate speech, document classification, and sentiment analysis. Experiments demonstrate that BengFastText can capture the semantics of words from respective contexts correctly. Evaluations against several baseline embedding models, e.g., Word2Vec and GloVe yield up to 92.30%, 82.25%, and 90.45% F1-scores in case of document classification, sentiment analysis, and hate speech detection, respectively during 5-fold cross-validation tests.