FRETA-D: A Toolkit of Automatic Annotation of Grammatical and Phonetic Error Types in French Dictations

Dictation is considered as an efficient practice for testing French as a Foreign Language (FFL) learners’ language proficiency. However, in-class dictation and teachers’ manual correction greatly reduce teaching efficiency. An existing dictation platform can only partly resolve these problems by providing instant error correction. To pursue better pedagogical feedback, this study develops an annotation toolkit called FRETA-D (FRench Error Type Annotation for Dictation), with an aim to provide more detailed error-type information for both FFL students and teachers. With parallel “learner input - reference text” sentences as input, FRETA-D can automatically identify error boundaries as well as classify and annotate the errors into fine-grained error types. Designed especially for French dictation, FRETA-D features a data-set-independent classifier based on a framework with 25 main error types, which is generated from French grammar rules and incorporates the characteristics of FFL learners’ common dictation errors. Five French teachers are invited to evaluate the appropriateness of the automatically predicted error types of 147 randomly chosen “error-correction” span pairs, and the acceptance rate reached more than 85%.