This paper presents the several strategies used and tested during the life of the ALLES project (IST-2001-34246) in order to achieve quality feedback in distance language learning. The purpose of the ALLES project was to show the feasibility to create more intelligent and individualised automatic correction modules on the basis of state-of-the-art linguistic technology. The paper describes how different error detection and correction strategies turn to be useful for different language learning tasks depending on its complexity and pedagogical requirements. In addition to two techniques specifically used to correct a specific language dimension –form or meaning–, we present an assessment methodology that combines the pieces of information provided by four different NLP-based processing and correction strategies to produce more communicative-oriented feedback, in line with the pedagogic model adopted by ALLES content developers. We present some testing and evaluations results –including testing with students– which are moderately positive and promising. Finally we discuss some issues of relevance to this research work.
[1]
Sylviane Granger,et al.
Automatic Profiling of Learner Texts
,
1998
.
[2]
Sandrine Garnier,et al.
Individualised NLP-enhanced feedback for distance language learning
,
2004,
IEEE International Conference on Advanced Learning Technologies, 2004. Proceedings..
[3]
Catherine Doughty,et al.
Focus on Form in Classroom Second Language Acquisition. The Cambridge Applied Linguistics Series.
,
1998
.
[4]
Toni Badia,et al.
NLP-enhanced Error Checking for Catalan Unrestricted Text
,
2004,
LREC.
[5]
Hans van Halteren,et al.
Linguistic profiling of texts for the purpose of language verification
,
2004,
COLING.
[6]
Sandrine Garnier,et al.
ALLES: Integrating NLP in ICALL Applications
,
2004,
LREC.
[7]
Michael Carl,et al.
Shallow Post Morphological Processing with KURD
,
1998,
CoNLL.
[8]
Randy M. Kaplan,et al.
Using Lexical Semantic Techniques to Classify Free-Responses
,
1999
.