GESJ: Computer Science and Telecommunications 2018|No.2(54) ISSN 1512-1232 76 AUTOMATIC QUESTION AND ANSWER GENERATION FROM BENGALI AND ENGLISH TEXTS Shudipta Sharma 1 , Muhammad Kamal Hossen 2 , Md. Sajjatul Islam 3 , Md. Shahnur Azad Chowdhury 4 , Md. Jiabul Hoque 5 1,2 Chittagong University of Engineering & Technology, 3 Chittagong Independent University, 4 International Islamic University Chittagong, 5 Southern University Bangladesh, Bangladesh 1 alittleprogramming@gmail.com, 2 kamalcsecuet@gmail.com, 3 sajjatcse99@gmail.com, 4 tipu_iiuc@yahoo.com, 5 jia99cse@yahoo.com Abstract The aim of this paper is to build a Question-Answering (QA) system considering Bengali and English language whose task is to generate questions along with their answers. There are two different process modules for Bengali and English. In each module, the main part is Question Generator (QG) which generates possible questions from a sentence by choosing a possible phrase as an answer-phrase. After that, the system has to perform some NLP tasks such as main verb decomposition, subject- auxiliary inversion (for English), replace answer-phrase with the question tag. Considering bivokti (), postfix and singular-plural, we have to choose the proper question tag and their form in Bengali. The selected answer-phrase for a question is used as the answer to that question. Another task of this system is to store the generated questions and their valid answers. Finally, the questions and their answers are displayed on the screen. The performance and accuracy of the system are evaluated on different Bengali and English texts. The performance of the system on question generation is 78.33% compared to the human being and the average percentage of accuracy of the generated questions is 76%. Keywords: Question Generator, NLP, Bengali-English, Answer-Phrase, Bilingual 1. Introduction If we ask that whether any interactive computer system about Question-Answering (QA) exists, the answer will be yes. But still, it is not so much. If there is a system that one can test by auto-generating different types of effective questions from some given texts as well as the answers for those questions, then it may be obviously helpful for him/her. Moreover, if it is bilingual, it will be an effective work for students as they may have academic subjects in two different languages (for example, Bengali and English in Bangladesh). So our goal is to design a QA system for Bengali and English. Generating raw questions along with answers can be a time consuming and effortful process. We have tried to do it here. Especially, the aim of the proposed system is to generate factual questions along with the answers from the texts. The system’s heart is a Question Generator (QG) that takes plain texts and gives a set of factual questions with the answers. A user can then select and revise them to create practice exercises or part of a quiz to assess whether students read the text and retained knowledge about its topic. We have motivated using informational, non-fiction texts that have factual information rather than opinions. And of course, here our work is not too much expert to do this. That expertise belongs to the future task.