Analyzing learner language: towards a flexible natural language processing architecture for intelligent language tutors

Abstract

Intelligent language tutoring systems (ILTS) typically analyze learner input to diagnose learner language properties and provide individualized feedback. Despite a long history of ILTS research, such systems are virtually absent from real-life foreign language teaching (FLT). Taking a step toward more closely linking ILTS research to real-life FLT, in this article we investigate the connection between FLT activity design and the system architecture of an ILT system. We argue that a demand-driven, annotation-based natural language processing (NLP) architecture is well-suited to handle the demands posed by the heterogeneous learner input which results when supporting a wider range of FLT activity types. We illustrate how the unstructured information management architecture (UIMA) can be used in an ILTS, thereby connecting the specific needs of activities in foreign language teaching to the current research and development of NLP architectures in general. Making the conceptual issues concrete, we discuss the design and realization of a UIMA-based reimplementation of the NLP in the TAGARELA system, an intelligent web-based tutoring system supporting the teaching and learning of Portuguese.Keywords: intelligent language tutoring systems (ILTS); intelligent computerassisted language learning (ICALL); natural language processing (NLP); unstructured information management architecture (UIMA); demand-driven annotation-based architecture; individualized feedback

Efficacy of an ICALL tutoring system and process-oriented corrective feedback

“…This would especially benefit elementary school students who typically experience difficulty utilizing the ICALL system. A more advanced version of the ICALL tutoring system that incorporates learner corpus (Amaral, Meurers, & Ziaib, 2011) is expected to provide individualized diagnostic feedback for EFL learners based on their responses to questions in at least a guided writing task. A more sophisticated NLP technology including a robust parser is required for future research to be able to provide individually tailored feedback in a more interactive manner and to maximize learner uptake.…”

Computational Methods for Corpus Annotation and Analysis

“…However, most of the work so far has focused on specific types of errors or relatively constrained sets of errors. Heift and Schulze (2007), Nagata (2009), andAmaral et al (2011) discussed different ways in which current natural language processing technology can be adapted to detect learner errors in the context of intelligent computer-assisted language learning. De Felice and Pulman (2008) proposed a classifier-based approach to the automatic detection and correction of preposition and determiner errors in L2 English writing.…”

A dynamic online system for translation learning and testing

“…This dynamic system is only a pilot project. Up to the present, enormous difficulties concerning natural language processing have emerged (Amaral, Meurers, & Ziai, 2011). For example, finding a good algorithm for the feedback module to determine the type of translation errors poses a great challenge.…”