Dynamic Question Answer Generator: An Enhanced Approach to Question Generation

Abstract

Teachers and educational institutions seek new questions with different difficulty levels for setting up tests for their students. Also, students long for distinct and new questions to practice for their tests as redundant questions are found everywhere. However, setting up new questions every time is a tedious task for teachers. To overcome this conundrum, we have concocted an artificially intelligent system which generates questions and answers for the mathematical topic-Quadratic equations. The system uses-i) Randomization technique for generating unique questions each time and ii) First order logic and Automated deduction to produce solution for the generated question. The goal was achieved and the system works efficiently. It is robust, reliable and helpful for teachers, students and other organizations for retrieving Quadratic equations questions, hassle-free.

Risk Analysis of AIGC in Market Regulation

“…Popular research directions in NLG include text summarization, text expansion, text rewriting, question answering, and dialogue systems. Text summarization involves compressing long texts into shorter ones, typically including tasks such as text summarization [5], question generation [6], and distractor generation [7]. Text extension tasks are to generate complete sentences or texts through meaningful words, such as short text expansion [8] and topic writing [9].…”

A Survey of Natural Language Generation

“…A further text-to-text generation complication is dividing NLG tasks into three categories, i.e., text abbreviation, text expansion, text rewriting and reasoning. The text abbreviation task is formulated to condense information from long texts to short ones, typically including research on text summarization [6,7,15,17,43,80,99], question generation [4,18,34,36,53,95,104,112,113,130,134], and distractor generation [22,50,60,73,82,86,100,101]. The text expansion tasks, such as short text expansion [5,89,96,106] and topic-to-essay generation [19,81,114,123,129], generate complete sentences or even texts from some meaningful words by considering and adding elements like conjunctions and prepositions to transform the input words into linguistically correct outputs.…”

“…Text Summarization MASS [99] PLM + Seq2Seq BART [43] PLM + Seq2Seq RCT [6] PLM + RNN + CNN + Seq2Seq + Long-term Dependency ProphetNet [80] PLM + Seq2Seq + Long-term Dependency En-semantic-model [15] RNN + Seq2Seq + Long-term Dependency Post-editing Factual Error Corrector [7] PLM + Seq2Seq + Factual Consistency SpanFact [17] PLM + Seq2Seq + Factual Consistency Question Generation Key-phrase-based Question Generator [18] Keyphrase + Template Dynamic Mathematical Question Generator [4] Constraint Handling Rules KB-based Factoid Question Generator [95] RNN + Seq2Seq Teacher Forcing and RL Based Question Generator [130] RNN + Seq2Seq + RL Paragraph-level Question Generator [134] RNN + Seq2Seq Answer-focused and Position-aware Question Generator [104] RNN + Seq2Seq + Answer-focused ASs2s [36] RNN + Seq2Seq + Answer-focused NQG-MP [113] RNN + Seq2Seq + Multi-task Paraphrase Enhaced Question Generator [34] RNN + Seq2Seq + Multi-task CGC-QG [53] RNN + Seq2Seq + Multi-task + GNN PathQG [112] RNN + Seq2Seq + Multi-task + KG…”

“…where [ | ] is the probability that a key-phrase has a × score , [ | ] is the probability that it has a distance , and [ , ] is the normalization factor. Bhatia et al [4] propose a dynamic question answering generator to generate questions and answers for the mathematical topic-quadratic equations. The randomization technique, first order logic and automated deduction are used for the study.…”