Automated Question Generation System for Genesis
Automatic Question Generation systems automatically generate questions from input such as text. This study implements an Automated Question Generation system for Genesis, a program that analyzes text. The Automated Question Generation system for Genesis outputs a ranked list of questions over conten...
| Main Author: | |
|---|---|
| Format: | Technical Report |
| Language: | en_US |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/121129 |
| _version_ | 1826209449297051648 |
|---|---|
| author | Lala, Sayeri |
| author_facet | Lala, Sayeri |
| author_sort | Lala, Sayeri |
| collection | MIT |
| description | Automatic Question Generation systems automatically generate questions from input such as text. This study implements an Automated Question Generation system for Genesis, a program that analyzes text. The Automated Question Generation system for Genesis outputs a ranked list of questions over content Genesis does not understand. It does this using a Question Generation Module and Question Ranking module. The Question Generation Module determines what content Genesis does not understand and generates questions using rules. The Question Ranking Module ranks the questions by relevance. This Automated Question Generation system was evaluated on a story read by Genesis. The average question relevance among the top 10 generated questions was 2.41 on a scale of 1-3, with 3 being most relevant. 53.8% of subjects ranked questions in the same order as the Question Ranking Module. The results suggest that the Automated Question generation system produces an optimally ranked list of relevant questions for Genesis. |
| first_indexed | 2024-09-23T14:22:41Z |
| format | Technical Report |
| id | mit-1721.1/121129 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:22:41Z |
| publishDate | 2019 |
| record_format | dspace |
| spelling | mit-1721.1/1211292019-04-12T23:06:23Z Automated Question Generation System for Genesis Lala, Sayeri computational models of human intelligence story understanding automated question generation question ranking Automatic Question Generation systems automatically generate questions from input such as text. This study implements an Automated Question Generation system for Genesis, a program that analyzes text. The Automated Question Generation system for Genesis outputs a ranked list of questions over content Genesis does not understand. It does this using a Question Generation Module and Question Ranking module. The Question Generation Module determines what content Genesis does not understand and generates questions using rules. The Question Ranking Module ranks the questions by relevance. This Automated Question Generation system was evaluated on a story read by Genesis. The average question relevance among the top 10 generated questions was 2.41 on a scale of 1-3, with 3 being most relevant. 53.8% of subjects ranked questions in the same order as the Question Ranking Module. The results suggest that the Automated Question generation system produces an optimally ranked list of relevant questions for Genesis. 2019-04-01T12:59:18Z 2019-04-01T12:59:18Z 2019-04-01 Technical Report http://hdl.handle.net/1721.1/121129 en_US CMHI Reports;4 application/pdf |
| spellingShingle | computational models of human intelligence story understanding automated question generation question ranking Lala, Sayeri Automated Question Generation System for Genesis |
| title | Automated Question Generation System for Genesis |
| title_full | Automated Question Generation System for Genesis |
| title_fullStr | Automated Question Generation System for Genesis |
| title_full_unstemmed | Automated Question Generation System for Genesis |
| title_short | Automated Question Generation System for Genesis |
| title_sort | automated question generation system for genesis |
| topic | computational models of human intelligence story understanding automated question generation question ranking |
| url | http://hdl.handle.net/1721.1/121129 |
| work_keys_str_mv | AT lalasayeri automatedquestiongenerationsystemforgenesis |