Language transfer, the characteristic second language usage patterns caused by native language interference, is investigated by Second Language Acquisition (SLA) researchers seeking to find overused and underused linguistic features. In this paper we develop and present a methodology for deriving ranked lists of such features. Using very large learner data, we show our method’s ability to find ...

This paper highlights the objectives and activities of the European project “RFID from Farm to Fork”, which is focused on the food industry traceability. The final goal is to extend the traceability information to the final consumer, so these persons could feel the confidence on the food origin like our grandparents did when they lived in a less globalised World. The activities of the project i...

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...

This paper describes the challenges faced by frontier technology education, typical among large integrated EU projects. These include an evolving nature, the scarcity of experts and established material, and the need for relevant material. Classical approaches to learning seem to not adequately address the needs of frontier technology alone. Following this observation we develop a training mode...

Public and industry concerns over food safety have grown considerably over the last decade. Food safety has traditionally been viewed as a “cost of business” (Littlefield, 2006) and, as a result, perceived and positioned as the voluntary responsibility of companies. However, this perception is changing as stricter legislation and industry standards are entered into force and require that compan...

Native Language Identification (NLI) is a task aimed at determining the native language (L1) of learners of second language (L2) on the basis of their written texts. To date, research on NLI has focused on relatively small corpora. We apply NLI to the recently released EFCamDat corpus which is not only multiple times larger than previous L2 corpora but also provides longitudinal data at several...