ERIC Number: ED618427
Record Type: Non-Journal
Publication Date: 2021-Jun-15
Pages: 10
Abstractor: As Provided
ISBN: N/A
ISSN: EISSN-
EISSN: N/A
Contextual Definition Generation
Yarbro, Jeffrey T.; Olney, Andrew M.
Grantee Submission, Paper presented at the International Workshop on Intelligent Textbooks (3rd, 2021)
This paper explores the concept of dynamically generating definitions using a deep-learning model. We do this by creating a dataset that contains definition entries and contexts associated with each definition. We then fine-tune a GPT-2 based model on the dataset to allow the model to generate contextual definitions. We evaluate our model with human raters by generating definitions using two context types: short-form (the word used in a sentence) and long-form (the word used in a sentence along with the prior and following sentences). Results indicate that the model performed significantly better when generating definitions using short-form contexts. Additionally, we evaluate our model against human-generated definitions. The results show promise for the model, showing that the model was able to match human-level fluency. However, while it was able to reach human-level accuracy in some instances, it failed in others. [This paper was published in: "Proceedings of the Third International Workshop on Intelligent Textbooks," Vol. 2895, CEUR-WS.org, 2021, pp. 74-83.]
Descriptors: Definitions, Learning Processes, Models, Context Effect, Evaluators, Sentences, Computational Linguistics, Accuracy, Textbooks, Vocabulary Development, Collaborative Writing, Multiple Choice Tests, Higher Education, Computer Software, Interrater Reliability, Editing, Web 2.0 Technologies, Web Sites
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: Higher Education; Postsecondary Education
Audience: N/A
Language: English
Sponsor: National Science Foundation (NSF); Institute of Education Sciences (ED)
Authoring Institution: N/A
IES Funded: Yes
Grant or Contract Numbers: 1918751; 1934745; R305A190448