Neural machine translation for automated feedback on children's early-stage writing
This addresses the need for automated feedback tools in education for young learners, though it appears incremental as it adapts existing translation methods to a specific domain.
The paper tackled the problem of automatically assessing and providing feedback on children's early-stage writing, which is challenging due to phonetic spelling and poor grammar, by using sequence-to-sequence models to translate it into conventional text, achieving high accuracy in prediction.
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 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.