Enhancing Grammatical Error Correction Systems with Explanations
This work addresses the need for better explanations in grammatical error correction for language learners, though it is incremental as it builds on existing GEC systems.
The authors tackled the problem of making grammatical error correction systems more understandable by introducing EXPECT, a dataset annotated with evidence words and error types, and found that their explainable system helps second-language learners decide on corrections and grasp grammar rules.
Grammatical error correction systems improve written communication by detecting and correcting language mistakes. To help language learners better understand why the GEC system makes a certain correction, the causes of errors (evidence words) and the corresponding error types are two key factors. To enhance GEC systems with explanations, we introduce EXPECT, a large dataset annotated with evidence words and grammatical error types. We propose several baselines and analysis to understand this task. Furthermore, human evaluation verifies our explainable GEC system's explanations can assist second-language learners in determining whether to accept a correction suggestion and in understanding the associated grammar rule.