Work

Transformer-Based Real-Word Spelling Error Feedback with Configurable Confusion Sets

Year: 2025

Type: conference-paper

Abstract: Real-word spelling errors (RWSEs) pose special challenges for detection methods, as they 'hide' in the form of another existing word and in many cases even fit in syntactically.We present a modern Transformer-based implementation of earlier probabilistic methods based on confusion sets and show that RWSEs can be detected with a good balance between missing errors and raising too many false alarms.The confusion sets are dynamically configurable, allowing teachers to easily adjust which errors trigger feedback.1.The name comes from the Greek work [word] for sun.2. These plants are more tolerance [tolerant] to drought.

Source: Workshop on Innovative Use of NLP for Building Educational Applications

DOI: 10.18653/v1/2025.bea-1.29

Authors: Torsten Zesch, Dominic Gardner, Marie Bexte

Institution: FernUniversität in Hagen

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: hybrid

OpenAlex ID: W4412889239