Automatic Question Generation via Semantic Role Labeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual generation of questions from text is time-consuming and inefficient, particularly in educational settings, necessitating the development of automatic question generation systems for assessing reading and language skills.
Innovation Solution
A computer-implemented system utilizing a semantic role-based approach to automatically generate questions from text by parsing sentences, assigning semantic role labels, and formulating questions based on these labels, capable of producing both wh-questions and yes-or-no questions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual generation of questions from text is used, then question quality can be controlled, but the process is time-consuming and inefficient
Solution Approach 1:
The patent replaces the manual mechanical process of question generation with an automated computational system. The system uses natural language processing, semantic role labeling, and template-based generation to automatically create questions from text, eliminating the need for manual intervention while maintaining question quality through structured linguistic analysis.
2Productivity
If automatic question generation systems are developed, then efficiency is improved, but system complexity increases
Solution Approach 1:
The patent segments the question generation process into distinct modular components: text parsing, semantic role labeling, question type selection, and template-based generation. Each component handles a specific aspect of the task, making the overall system more manageable and easier to implement while achieving high automation efficiency.
Solution Approach 2:
The patent introduces semantic role labels as an intermediary representation between the input text and the generated questions. This intermediate layer captures the semantic structure of the text in a standardized format that can be systematically transformed into various question types, simplifying the overall generation process.
3Measurement precision
If semantic role-based approach is used, then question accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent performs semantic role labeling as a preliminary step before question generation. By pre-processing the text to identify and label semantic roles (such as agent, patient, instrument, location, time), the system establishes a structured foundation that guides subsequent question formation, ensuring accuracy while organizing the processing complexity into manageable stages.
Data Source
AI summary
Computer-implemented systems and methods are described herein for automatically generating questions from text. Text including one or more sentences is received. A sentence, comprising a predicate and one or more arguments associated with the predicate, is parsed from the text. Semantic role labels are assigned to the one or more arguments associated with the predicate. One or more questions are automatically generated relating to the predicate based on the assigned semantic role labels. Each answer to the generated questions is one of the one or more arguments associated with the predicate.