Tapping into the Power of Automatic Question Generation

Abstract

ABSTRACT Question Generation (QG) is an important element of learning environments, information seeking systems, help systems, and other applications. There are a number of distinct research subfields which are concerned with the Automatic Question Generation (AQG) Systems. This research tries to have a wide look on existing automatic question generation systems, and some trials of overcoming its difficulties from different points of views . General Terms Natural Language Processing, Natural Language Generation questions) whereas sha Keywords Automatic Question Generation, Questions Taxonomy, Multiple Choice Questions, Entity Based Questions. 1. INTRODUCTION Questions have been studied as part of the task of Question Answering in the field of Natural Language Processing (NLP). At the beginning, question answering research focused on answering questions from databases and knowledge representations [1], but in the past two decades has refocused on retrieving answers from text – e.g., in 1999 the evaluation of question-answering systems became part of the Text Retrieval Conference (TREC) series. Simultaneously, there has been a strand of research on advisory dialogue systems [2]. All the previous systems were primarily aimed at responding to the user’s questions. Recently, there has been a broader transformation in the field of Natural Language Processing researches in Question Generation task. Since 2008, researchers from different communities, such as, Discourse Analysis, Dialogue Modeling, Formal Semantics, Intelligent Tutoring Systems, Natural Language Generation, Natural Language Understanding, and Psycholinguistics, have met annually at the Question Generation workshop. AQG system would be useful for building an automated trainer for learners to ask better questions, and for building a better hint and question asking facilities in intelligent tutoring systems [3]. Another benefit of QG is that it can be a good tool to help in improving the quality of the Question Answering (QA) systems. Available studies revealed that humans were not very skilled in asking good questions. Therefore, they would benefit from automated QG systems to assist them in meeting their inquiry needs [4]. In this research, a survey about automatic question generation and different variety of work that has been done is discussed. The rest of the paper is organized as follows: section 2 discusses the basic steps for automatic question generation systems; section 3 introduces two distinct taxonomies of questions, section 4 the state of the art in which a description of the previous work, finally section 5 introduces a conclusion with some remarks.