Paraphrased Question Answering Using Recurrent Neural Network in Bangla Language

Abstract

Recent studies on QA (Question Answering) system in English language have been emerged extensively with the composition of NLP (Natural Language Processing) and IR (Information Retrieval) by amplifying miniature sub tasks to accomplish a whole AI-system having capability of answering and reasoning complicated and long questions through understating paragraph. In our proposed study, we present a general heuristic framework, an end-to-end model used for paraphrased question answering using single supporting line which is the initial appearance ever in Bangla language. Corpus dataset was scrapped from Bangla wiki and then questions were generated corresponding context have been used to learn the model. Translated bAbI dataset (1 supporting fact) [5][6] in Bangla language has been also incorporated with to experiment the proposed model manually. To predict appropriate answer, model is trained with question-answer pair and a supporting line. For comparing our task applying variation of basic RNN (Recurrent Neural Network): LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit) different accuracy has been found. For further accomplishment, synthetic and semantic word relevance in high dimension vector space: Bangla Word2vec (word embedding system) is added to the system as sentence representation along with PE (Positioning Encoding) and which outperforms both memory network GRU and LSTM precisely.