In this paper we present a survey of some most significant spoken English learner corpora created up to date. Spoken learner corpora which include speech generated by learners are important in many areas of research and practice, in particular, for identifying typical pronunciation errors of learners of English as a second language (ESL), English as a foreign language (EFL), or English as a lin...

With the aim of storing learner corpora as well as information about the Basque language students who wrote the texts, two different but complementary databases were created: ERREUS and IRAKAZI. Linguistic and technical information (error description, error category, tools for detection/correction...) will be stored in ERREUS, while IRAKAZI will be filled in with psycholinguistic information (e...

In this paper we aim to describe the process by which our personalised web-based collaborative teaching/learning methodology (CECIP – Collaboration – Evaluation – Critical thinking – Individual assessment – learner Profile) evolved originating from Vygotsky’s theory and based on the (C) collaborative construction of student’s knowledge, (E) developing evaluation and assessment skills, (C) devel...

In this paper, the authors present their proposal for adaptation of educational contents of learning objects to a particular mobile device and a specific learner. Content adaptation in mobile learning objects implies user adaptation and device adaptation, and requires additional metadata categories in comparison with SCORM 2004. This learning object content model, ALMA (A Learning content Model...

In uncertain and partially observable environments control policies must be a function of the complete history of actions and observations. Rather than present an ever growing history to a learner, we instead track sufficient statistics of the history and map those to a control policy. The mapping has typically been done using dynamic programming, requiring large amounts of memory. We present a...