Classifying Syntactic Errors in Learner Language
This provides a cross-linguistic tool for analyzing syntactic errors in language learners, though it builds incrementally on existing Universal Dependencies representations.
The researchers developed a method for classifying syntactic errors in learner language that works across multiple languages, demonstrating it on English and Russian learner data and showing its utility for analyzing grammatical error correction systems.
We present a method for classifying syntactic errors in learner language, namely errors whose correction alters the morphosyntactic structure of a sentence. The methodology builds on the established Universal Dependencies syntactic representation scheme, and provides complementary information to other error-classification systems. Unlike existing error classification methods, our method is applicable across languages, which we showcase by producing a detailed picture of syntactic errors in learner English and learner Russian. We further demonstrate the utility of the methodology for analyzing the outputs of leading Grammatical Error Correction (GEC) systems.