Automatic English Question Generation System Based on Template Driven Scheme Hafedh Hussein 1 , Mohammed Elmogy 2 and Shawkat Guirguis 3 1 Information Technology Department, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt 2 Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura, P.O. 35516, Egypt 3 Information Technology Department, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt Abstract Today, automatic generation of questions is a considerable problem by many researchers. Automatic question generation from text has two major activity domains: dialogue/interactive question answering systems and educational assessment. In this paper, a proposed system is designed, implemented and tested to automate question generation process. The proposed system generates questions by selecting one sentence at a time, extracts sections of the source sentence, then applies transformation rules or patterns for constructing a question. It uses pure syntactic pattern-matching approach to generate content-related questions in order to improve the independent study of any textual material. The proposed system is powered by OpenNLP open source statistical parser to generate the questions using pattern matching strategy. The system is able to learn dynamically, ready to use in ease manner and accepts large-scale number of rules. Keywords: Natural Language Processing, Parsing, Question Generation, Questionnaire System. 1. Introduction In addition to real life discussions, questions are the significant fundamental immeasurable learning interactions from one-to-one education sessions to extensive assessments. Human has usually natural curious because of self-satisfaction of his never ending requirements of knowledge. Question is a helpful tool for performance evaluation of students. Our day-to-day lives involve asking questions in conversations and dialogues to render a meaningful co-operative society. Because humans are almost subject to ambiguous, busy, or inconsistent mind in certain situations, question generation problem was raised to be solved and researched by many researchers over the last decade years. Therefore, the potential benefits from an automated Question Generation (QG) system could assist humans in meeting their useful inquiry needs such as education, knowledge based, daily activities, and much more application(s) [1]. QG has turned into an essential element of learning environments, help systems, information seeking systems…etc. Considerable interest from the Natural Language Processing (NLP), Natural Language Generation (NLG), Intelligent Tutoring System, and Information Retrieval (IR) communities have currently identified the Text-to-Question generation task as a promising candidate for the shared task [2, 3]. In the Text- to-Question generation phase, a QG system starts by a given text and its goal would be to generate a set of questions for which the text contains answers [4]. To generate a question from a given sentence, the system must processes the sentence to get elementary items of the text. In such systems, sentence processing is a subject to NLP fields of computer science [2]. There are many researches focus on building up algorithms, techniques, and methodologies for processing natural language sentences. OpenNLP and IXA [27] pipelines are the most popular open source NLP API and software development kit that are ready to use for parsing and automatic understanding of English sentences that are powered by researchers results over years. Question in natural language is a unit of language that can be classified into different categories as follow [10, 11]:  Factoid Questions: They are questions that are used to ask for fact-based answers. They use one of these question tools: What, Where, When, Who, or How.  List Questions: They are questions that are used to ask for a set of answer terms. They use “which” as a question tool. IJCSI International Journal of Computer Science Issues, Volume 11, Issue 6, No 1, November 2014 ISSN (Print): 1694-0814 | ISSN (Online): 1694-0784 www.IJCSI.org 45 2014 International Journal of Computer Science Issues