Back to grammar: Using grammatical error correction to automatically assess L2 speaking proficiency

Open Webpage

Stefano Bannò, Marco Matassoni

Published: 01 Jan 2024, Last Modified: 06 Oct 2025Speech Commun. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Using grammatical features can enhance assessment performance and validity.•Our pipeline can provide insights about proficiency and feedback on spoken grammar.•Disfluency removal improves spoken grammatical error correction.•Grammatical error correction can be performed by only using public data.