Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network

: Karim, M.R.; Chakravarthi, B.R.; McCrae, J.P.; Cochez, M.


Webb, G. ; Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020. Proceedings : 6-9 October 2020, Sydney, Australia
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2020
ISBN: 978-1-7281-8206-3
ISBN: 978-1-7281-8207-0
International Conference on Data Science and Advanced Analytics (DSAA) <7, 2020, Online>
Conference Paper
Fraunhofer FIT ()

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 behavior like online harassment, cyberbul-lying, and hate speech. Numerous works have been proposed to utilize these data for social and anti-social behavior analysis, document characterization, and sentiment analysis by predicting the contexts mostly for highly resourced languages like English. However, some languages are under-resources, e.g., South Asian languages like Bengali, Tamil, Assamese, Malayalam, that lack of computational resources for natural language processing. In this paper1, 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. We built the largest Bengali word embedding models to date based on 250 million articles, which we call BengFastText. We perform three experiments, covering document classification, sentiment analysis, and hate speech detection. We incorporate word embeddings into a Multichannel Convolutional-LSTM (MC-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.