Neural machine translation for automated feedback on children’s early-stage writing

Jonas Vestergaard Jensen*, Mikkel Jordahn, Michael Riis Andersen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

19 Downloads (Pure)

Abstract

In this work, we address the problem of assessing and constructing feedback for early-stage writing automatically using machine learning. Early-stage writing is typically vastly different from conventional writing due to phonetic spelling and lack of proper grammar, punctuation, spacing etc. Consequently, early-stage writing is highly non-trivial to analyze using common linguistic metrics. We propose to use sequence-to-sequence models for translating early-stage writing by students into conventional writing, which allows the translated text to be analyzed using linguistic metrics. Furthermore, we propose a novel robust likelihood to mitigate the effect of label noise in the dataset. We investigate the proposed methods using a set of numerical experiments and demonstrate that the conventional text can be predicted with high accuracy.
Original languageEnglish
Title of host publicationProceedings of the 5th Northern Lights Deep Learning Conference
Volume233
PublisherProceedings of Machine Learning Research
Publication date2024
Pages104-112
Publication statusPublished - 2024
Event 5th Northern Lights Deep Learning Conference - Tromsø, Norway
Duration: 9 Jan 202411 Jan 2024
Conference number: 5

Conference

Conference 5th Northern Lights Deep Learning Conference
Number5
Country/TerritoryNorway
CityTromsø
Period09/01/202411/01/2024

Fingerprint

Dive into the research topics of 'Neural machine translation for automated feedback on children’s early-stage writing'. Together they form a unique fingerprint.

Cite this