The paper presents two knowledge-based approaches to the design of intelligent tutoring systems focusing on diagnosing students and generating adaptive explanations. We discuss the use of a domain ontology encoded with conceptual graphs in two recent works in Artificial Intelligence in Education and Natural Language Processing: STyLE-OLM (an interactive learner modelling system that extracts ex...

We discuss making syntactic annotation for learner language more precise, by clarifying the properties which the layers of annotation refer to. Building from previous proposals which split linguistic annotation into multiple layers to capture non-canonical properties of learner language, we lay out the questions which must be asked for grammatical annotation and provide some answers. Our invest...

Intelligent computer-assisted language learning (ICALL) systems give feedback on grammatical errors based on the syntactic analysis of an utterance. However, parsing a language learner sentence in isolation can result in multiple interpretations, which even humans may not be able to resolve. For deriving a helpful error diagnosis, an interpretation that is consistent with the intended meaning i...

We apply a memory-based learner to the CoNLL-2002 shared task: language-independent named entity recognition. We use three additional techniques for improving the base performance of the learner: cascading, feature selection and system combination. The overall system is trained with two types of features: words and substrings of words which are relevant for this particular task. It is tested on...

Conclusion Context: A sketch of our research perspective Analyzing learner language I Intelligent Tutoring System TAGARELA for Portuguese (Amaral & Meurers 2008, 2009, 2011; Amaral et al. 2011) I Automatic analysis of learner language (Meurers 2009) I Linguistic analysis of NOCE corpus of English written by Spanish learners (Dı́az-Negrillo, Meurers, Valera & Wunsch 2010) I Word order errors (Met...

_________________________________________________________________________________________________________ Of the Use of Natural Dialogue to Hide MCQs in Serious Games A major weakness of serious games at the moment is that they often incorporate multiple choice questionnaires (MCQs). However, no study has demonstrated that MCQs can accurately assess the level of understanding of a learner. On t...

In learner corpora, as in any corpus, mark-up is an important issue. One aspect of learner corpora so far largely ignored, however, is the specific question of handwriting and in particular how to mark-up handwriting anomalies, especially with learners whose native language uses a different writing system. In this paper we pose some open questions about what aspects of a learner’s handwriting m...

Researchers working with learner corpora promise quantitative results that would be of greater practical value in areas such as CALL than those from small-scale and qualitative studies. However, learner corpus research has not yet had an impact on practices in teaching and assessment. Significant methodological issues need to be examined if results from learner corpus research are going to prov...

This paper presents the mechanisms of and criteria for compiling a new learner corpus of English, the quantitative characteristics of the corpus and a practical example of its pedagogical application. The Taiwanese Learner Corpus of English (TLCE), probably the largest annotated learner corpus of English in Taiwan so far, contains 2105 pieces of English writing (around 730,000 words) from Taiwa...