This paper investigates the suitability of state-of-the-art natural language processing (NLP) tools for parsing the spoken language of second language learners of English. The task of parsing spoken learner-language is important to the domains of automated language assessment (ALA) and computer-assisted language learning (CALL). Due to the non-canonical nature of spoken language (containing filled pauses, nonstandard grammatical variations, hesitations and other disfluencies) and compounded by a lack of available training data, spoken language parsing has been a challenge for standard NLP tools. Recently the Redshift parser (Honnibal et al. In: Proceedings of CoNLL (2013)) has been shown to be successful in identifying grammatical relations and certain disfluencies in native speaker spoken language, returning unlabelled dependency accuracy of 90.5% and a disfluency F-measure of 84.1% (Honnibal & Johnson: TACL 2, 131-142 (2014)). We investigate how this parser handles spoken data from learners of English at various proficiency levels. Firstly, we find that Redshift's parsing accuracy on non-native speech data is comparable to Honnibal & Johnson's results, with 91.1% of dependency relations correctly identified. However, disfluency detection is markedly down, with an F-measure of just 47.8%. We attempt to explain why this should be, and investigate the effect of proficiency level on parsing accuracy. We relate our findings to the use of NLP technology for CALL and ALA applications.
