Do deep neural nets display human-like attention in short answer scoring?

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

Deep Learning (DL) techniques have been increasingly adopted for Automatic Text Scoring in education. However, these techniques often suffer from their inabilities to explain and justify how a prediction is made, which, unavoidably, decreases their trustworthiness and hinders educators from embracing them in practice. This study aimed to investigate whether (and to what extent) DL-based graders align with human graders regarding the important words they identify when marking short answer questions. To this end, we first conducted a user study to ask human graders to manually annotate important words in assessing answer quality and then measured the overlap between these human-annotated words and those identified by DL-based graders (i.e., those receiving large attention weights). Furthermore, we ran a randomized controlled experiment to explore the impact of highlighting important words detected by DL-based graders on human grading. The results showed that: (i) DL-based graders, to a certain degree, displayed alignment with human graders no matter whether DL-based graders and human graders agreed on the quality of an answer; and (ii) it is possible to facilitate human grading by highlighting those DL-detected important words, though further investigations are necessary to understand how human graders exploit such highlighted words.

Original languageEnglish
Title of host publicationNAACL 2022 - The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
EditorsMarie-Catherine de Marneffe, Marine Carpuat, Ivan Vladimir Meza Ruiz
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Pages191-205
Number of pages15
ISBN (Electronic)9781955917711
DOIs
Publication statusPublished - 2022
EventNorth American Association for Computational Linguistics 2022: NAACL 2022 - Seattle, United States of America
Duration: 10 Jul 202215 Jul 2022
https://aclanthology.org/volumes/2022.findings-naacl/

Conference

ConferenceNorth American Association for Computational Linguistics 2022
Country/TerritoryUnited States of America
CitySeattle
Period10/07/2215/07/22
Internet address

Cite this