Alexandra Lavrentovich


2018

pdf bib
Using Classifier Features to Determine Language Transfer on Morphemes
Alexandra Lavrentovich
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop

The aim of this thesis is to perform a Native Language Identification (NLI) task where we identify an English learner’s native language background based only on the learner’s English writing samples. We focus on the use of English grammatical morphemes across four proficiency levels. The outcome of the computational task is connected to a position in second language acquisition research that holds all learners acquire English grammatical morphemes in the same order, regardless of native language background. We use the NLI task as a tool to uncover cross-linguistic influence on the developmental trajectory of morphemes. We perform a cross-corpus evaluation across proficiency levels to increase the reliability and validity of the linguistic features that predict the native language background. We include native English data to determine the different morpheme patterns used by native versus non-native English speakers. Furthermore, we conduct a human NLI task to determine the type and magnitude of language transfer cues used by human raters versus the classifier.
Search
Co-authors
    Venues