Integrating learner corpora and natural language processing: A crucial step towards reconciling technological sophistication and pedagogical effectiveness
Résumé
While the field of Technology-Enhanced Language Learning (TELL) is undeniably thriving, most technology-enhanced language tools are still relatively crude. One reason for this is that the field is disconnected from research in Natural Language Processing (NLP) and Corpus Linguistics (CL), two fields which could greatly improve the effectiveness of most pedagogical tools. The research carried out within the framework of the Kaleidoscope Network of Excellence aimed to demonstrate that it is both possible and desirable to integrate insights from NLP and CL into TELL to produce more powerful and effective tools. In the article we give a general outline of NLP and CL techniques and highlight their relevance for TELL. We also describe two types of integration that were implemented within the framework of Kaleidoscope: (1) integration of NLP processing into the glossary of the Moodle Learning Management System; (2) integration of error-tagged learner corpus data into Exxelant, a web-based error interface for teachers and researchers. The chapter also argues the case for optimising the role of language in all technology-enhanced learning applications, whether language-focused or not.