F8014038620

Questions Generation for Reading Comprehension using Coherence Relations
Anamika¹, Vibhakar Pathak², Vishal Shrivastava³, Akil Pandey^4
1Animika, Scholar, Department of computer Engineering, Arya College of Engineering, Kukus, Jaipur, Rajasthan, India.
²Dr. Vibhakar Pathak, Professor, Department of computer Engineering, Arya College of Engineering, Kukus, Jaipur, Rajasthan, India.
³Dr.Vishal Shrivastava, Professor, Department of computer Engineering, Arya College of Engineering, Kukus, Jaipur, Rajasthan, India.
⁴Dr. Akil, Professor, Department of computer Engineering, Arya College of Engineering, Kukus, Jaipur, Rajasthan, India.
Manuscript received on March 12, 2020. | Revised Manuscript received on March 25, 2020. | Manuscript published on March 30, 2020. | PP: 2741-2745 | Volume-8 Issue-6, March 2020. | Retrieval Number: F8014038620/2020©BEIESP | DOI: 10.35940/ijrte.F8014.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The present scenario requires a large amount of digital content in the context of forums, directories, videos, classes, etc. Questions can thus play a significant role in digital media by quizzes, questions. Producing Question is the job of automatically producing questions from natural language, acting as one of the main fields of natural language human-computer interaction. we focus on generating fact-seeking, questions using the knowledge base. We implemented a system that takes a reading comprehension text as input and outputs all questions for the selected domain. Our system makes the GQ process three-stage. 1. Content selection selected for question generation 2. Question formation (content transformations to get the question), 3. Evaluate the quality of generated question. The framework system is implemented as an end-to-end system that expects a human to specify a topic. The resulting output is a set of questions in natural language, that Follows the input domain. We show the effectiveness of our approach with previous Heilman and Smith MH method.
Keywords: Natural Language Generation, Question Generation, Semantic Role Labeling, Templates, Self-Directed Learning.
Scope of the Article: Machine Learning.