Evaluating Stages of Development in Second Language French: A Machine-Learning Approach

This paper describes a system to define and evaluate development stages in second language French. The identification of such stages can be formulated as determining the frequency of some lexical and grammatical features in the learners ’ production and how they vary over time. The problems in this procedure are threefold: identify the relevant features, decide on cutoff points for the stages, and evaluate the degree of success of the model. The system addresses these three problems. It consists of a morphosyntactic analyzer called Direkt Profil and a machine-learning module connected to it. We first describe the usefulness and rationale behind its development. We then present the corpus we used to develop the analyzer. Finally, we present new and substantially improved results on training machine-learning classifiers compared to previous experiments (Granfeldt et al., 2006). We also introduce a method to select attributes in order to identify the most relevant grammatical features.