Modeling informal inference in natural language is very challenging. With the recent availability of large annotated data, it has become feasible to train complex models such as neural networks to perform natural language inference (NLI), which have achieved state-of-the-art performance. Although there exist relatively large annotated data, can machines learn all knowledge needed to perform NLI...

We present a novel deep learning architecture to address the natural language inference (NLI) task. Existing approaches mostly rely on simple reading mechanisms for independent encoding of the premise and hypothesis. Instead, we propose a novel dependent reading bidirectional LSTM network (DR-BiLSTM) to efficiently model the relationship between a premise and a hypothesis during encoding and in...

This paper presents an ensemble system combining the output of multiple SVM classifiers to native language identification (NLI). The system was submitted to the NLI Shared Task 2017 fusion track which featured students essays and spoken responses in form of audio transcriptions and iVectors by non-native English speakers of eleven native languages. Our system competed in the challenge under the...

In this paper, we explore spelling errors as a source of information for detecting the native language of a writer, a previously under-explored area. We note that character n-grams from misspelled words are very indicative of the native language of the author. In combination with other lexical features, spelling error features lead to 1.2% improvement in accuracy on classifying texts in the TOE...

Attempts to profile authors based on their characteristics, including native language, have drawn attention in recent years, via several approaches using machine learning with simple features. In this paper we investigate the potential usefulness to this task of contrastive analysis from second language acquistion research, which postulates that the (syntactic) errors in a text are influenced b...

We outline the first application of Native Language Identification (NLI) to Finnish learner data. NLI is the task of predicting an author’s first language using writings in an acquired language. Using data from a new learner corpus of Finnish — a language typology quite different from others previously investigated, with its morphological richness potentially causing difficulties — we show that...

In this paper, we systematically explore lexicalized and non-lexicalized local syntactic features for the task of Native Language Identification (NLI). We investigate different types of feature representations in singleand cross-corpus settings, including two representations inspired by a variationist perspective on the choices made in the linguistic system. To combine the different models, we ...

This study explores the efficacy of an approach to native language identification that utilizes grammatical, rhetorical, semantic, syntactic, and cohesive function categories comprised of key n-grams. The study found that a model based on these categories of key n-grams was able to successfully predict the L1 of essays written in English by L2 learners from 11 different L1 backgrounds with an a...

We examine different ensemble methods, including an oracle, to estimate the upper-limit of classification accuracy for Native Language Identification (NLI). The oracle outperforms state-of-the-art systems by over 10% and results indicate that for many misclassified texts the correct class label receives a significant portion of the ensemble votes, often being the runner-up. We also present a pi...