A tool for automatic question generation for teaching english to beginner students

Abstract

We present a tool for the automatic generation of questions from texts for ESL teaching, using resources and methods from the Natural Language Processing (NLP) field. The approach presented in this paper is based on symbolic methods, using hand-crafted rules. The tool uses linguistic information, such as semantic roles, co-references and named entities, to generate questions and answers from a text selected by a teacher. The generated questions are ranked in order to offer the teacher a varied set to create an exercise. All the elements can be edited in case any error is produced, since NLP tools and methods are not completely accurate. When solving an exercise, the students are given immediate feedback based on the expected answers. A primary evaluation showed promising results, especially for “what” and “who” questions.