skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Friday, December 13 until 2:00 AM ET on Saturday, December 14 due to maintenance. We apologize for the inconvenience.


Title: Improving Reading Comprehension Question Generation with Data Augmentation and Overgenerate-and-rank
Award ID(s):
2202506 2237676
PAR ID:
10439396
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
Page Range / eLocation ID:
247 to 259
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Researchers emphasize the role of math and science identities in science, technology, engineering, and mathematics (STEM) education. However, little is known about whether these identities might evolve during college; likewise it is not known how changes in math and science identities are associated with switching majors between STEM and non-STEM fields. This study addresses these questions. With data from the Pathways through College Study, this study revealed that science identity changes matter more than math identity changes in their association with the decision to switch majors. Most notably, underrepresented racial minority women are the most vulnerable in terms of decreasing science identity and the associated probabilities of leaking out of STEM. The authors also find evidence that Asian students are the least sensitive to their science identity drop. These findings have significant policy implications with regard to STEM choice and attainment.

     
    more » « less