How can Writing Tasks be Characterized in a way serving Pedagogical Goals and Automatic Analysis Needs?

Abstract

The paper works out and addresses a central question in the field of Intelligent Computer-Assisted Language Learning (ICALL): How can language learning tasks be conceptualized and made explicit in a way that supports the pedagogical goals in modern Foreign Language Teaching and Learning (FLTL) and at the same time provides an explicit characterization of the Natural Language Processing (NLP) requirements to provide feedback to learners completing those tasks? We argue that the successful implementation of language learning tasks to be automatically assessed by means of NLP-based feedback generation strategies demands a design process considering both pedagogical and computational requirements as equally important.
 
 Extending well-established work in Task-Based Language Teaching (TBLT) and TBLT testing we propose a framework that helps us (i) elucidate the formal features of foreign language learning activities, (ii) characterize the gap between expected and actually elicited learner language, and (iii) assess how variability in learner responses impacts computational techniques for the automatic analysis of learner language.
 
 To validate our approach we apply our framework to two specific writing tasks for learners of English as a Foreign Language (EFL). Our analysis highlights the relevance of spelling out the pedagogical and linguistic goals of language learning tasks in order to successfully characterize the language variation in learner responses needed to design effective pedagogical and NLP strategies.Given the combination of design- and data-driven perspectives, the framework supports an iterative approach to the creation of language learning tasks and ICALL materials.