Norwegian Native Language Identification

Proceedings of Recent Advances in Natural Language Processing, pages 404–412, Hissar, Bulgaria, Sep 7–9 2015. Norwegian Native Language Identification Shervin Malmasi♦ Mark Dras♦ Irina Temnikova♥ ♦Macquarie University, Sydney, NSW, Australia ♥Qatar Computing Research Institute, HBKU, Qatar shervin.malmasi@mq.edu.au, mark.dras@mq.edu.au itemnikova@qf.org.qa Abstract We present a study of Native Language Identification (NLI) using data from learn- ers of Norwegian, a language not yet used for this task. NLI is the task of predicting a writer’s first language using only their writings in a learned language. We find that three feature types, function words, part-of-speech n-grams and a hy- brid part-of-speech/function word mixture n-gram model are useful here. Our sys- tem achieves an accuracy of 79% against a baseline of 13% for predicting an author’s L1. The same features can distinguish non-native writing with 99% accuracy. We also find that part-of-speech n-gram per- formance on this data deviates from previ- ous NLI results, possibly due to the use of manually post-corrected tags. 1 Introduction Native Language Identification (NLI) is the task of identifying a writer’s native language (L1) based only on their writings in a second language (the L2). NLI works by identifying language use pat- terns that are common to groups of speakers of the same native language. This process is underpinned by the presupposition that an author’s L1 disposes them towards certain language production patterns in their L2, as influenced by their mother tongue. This relates to cross-linguistic influence (CLI), a key topic in the field of Second Language Acqui- sition (SLA) that analyzes transfer effects from the L1 on later learned languages (Ortega, 2009). It has been noted in the linguistics litera- ture since the 1950s that speakers of particular languages have characteristic production patterns when writing in a second language. This lan- guage transfer phenomenon has been investigated independently in various fields from different per- spectives, including qualitative research in SLA and more recently though predictive computa- tional models in NLP (Jarvis and Crossley, 2012). Recently this has motivated studies in Native Language Identification (NLI), a subtype of text classification where the goal is to determine the native language (L1) of an author using texts they have written in a second language or L2 (Tetreault et al., 2013). The motivations for NLI are manifold. The use of such techniques can help SLA researchers iden- tify important L1-specific learning and teaching issues. In turn, the identification of such issues can enable researchers to develop pedagogical ma- terial that takes into consideration a learner’s L1 and addresses them. It can also be applied in a forensic context, for example, to glean informa- tion about the discriminant L1 cues in an anony- mous text. In fact, recent NLI research such as that related to the work presented by Perkins (2014) has already attracted interest and funding from in- telligence agencies (Perkins, 2014, p. 17). While most NLI research to date has focused on English L2 data, there is a growing trend to ap- ply the techniques to other languages in order to assess …

Content truncated to 500 words