DalTeam@INLI-FIRE-2017: Native Language Identification using SVM with SGD Training

Native Language Identification (NLI), as a variant of Language Identification task, focuses on determining an author’s native language, based on a writing sample in their non-native language. In recent years, the challenging nature of NLI has drawn much attention from the research community. Its application and importance are relevant in many fields, such as personalization of a new language learning environment, personalized grammar correction, and authorship attribution in forensic linguistics. We participated in the INLI Shared Task 2017 held in conjunction with FIRE 2017 conference. To implement a machine learning method for Native Language Identification, we used Character and Word N-grams with SVM (Support Vector Machines) classifier trained with SGD (Stochastic Gradient Descent) method. We achieved F1 measure of 89.60% (using 10-fold cross validation), using provided social media dataset and 48.80% was reported in the final testing done by INLI workshop organisers.