Intelligent Computer-assisted Language Learning System Research Articles

The effects of working memory and declarative memory on instructed second language vocabulary learning: Insights from intelligent CALL

The extent to which learners benefit from instruction may be largely dependent on their individual abilities. However, there is relatively little work on the interaction between instructional effectiveness in second language learning and learner individual factors. In this study, we investigated the relationship between instruction, individual differences in cognitive abilities (working memory and declarative memory), and second language vocabulary acquisition in the context of web-based intelligent computer assisted language learning (ICALL). To this end, 127 adult learners of English, predominantly advanced-level, German-speaking learners, read news texts on the web for about two weeks using an ICALL system under two instructional conditions: form-focused and meaning-focused instruction. Learners in the form-focused condition read and completed automatically-generated multiple-choice gaps where phrasal verbs appeared in the text, while learners in the meaning-focused condition simply read and did not complete any gaps. Mixed-effects regression analyses showed that working memory was associated with vocabulary acquisition and that this association depended on the instructional context, with working memory being predictive of learning only in the form-focused condition, suggesting an aptitude-treatment interaction. Furthermore, declarative memory abilities were related to learning only as measured by the Continuous Visual Memory Task, and the relationship was not moderated by instructional condition. Overall, the study contributes to accounting for variability in second language learning in general, as well as in instructional contexts supported by intelligent CALL.

Language Learning Research at the Intersection of Experimental, Computational, and Corpus‐Based Approaches

Language Learning Research at the Intersection of Experimental, Computational, and Corpus‐Based Approaches

Providing graduated corrective feedback in an intelligent computer-assisted language learning environment

AbstractCorrective feedback (CF), a response to linguistic errors made by second language (L2) learners, has received extensive scholarly attention in second language acquisition. While much of the previous research in the field has focused on whether CF facilitates or impedes L2 development, few studies have examined the efficacy of gradually modifying the explicitness or specificity of CF as a function of a learner’s response to the feedback. Yet, the type and extent of CF needed by a learner, as suggested by Vygotsky (1978), sheds light on whether a learner is developing his or her abilities in a particular area and the ways in which they do it. This paper reports on a study that explores the design, effectiveness and learners’ perception toward agraduated(Aljaafreh & Lantolf, 1994) approach to CF, i.e., feedback that progresses from very general and implicit to very specific and explicit, in an intelligent computer-assisted language learning (ICALL) environment. The results show that the graduated approach to CF is effective in helping learners to self-identify and self-correct a number of grammatical issues, although an onsite tutor provides necessary remedies when the ICALL system occasionally fails to do its part. Implications for CF research, particularly on the notion of individualized feedback, are also discussed.

Grammatical Error Detection for Corrective Feedback Provision in Oral Conversations

The demand for computer-assisted language learning systems that can provide corrective feedback on language learners’ speaking has increased. However, it is not a trivial task to detect grammatical errors in oral conversations because of the unavoidable errors of automatic speech recognition systems. To provide corrective feedback, a novel method to detect grammatical errors in speaking performance is proposed. The proposed method consists of two sub-models: the grammaticality-checking model and the error-type classification model. We automatically generate grammatical errors that learners are likely to commit and construct error patterns based on the articulated errors. When a particular speech pattern is recognized, the grammaticality-checking model performs a binary classification based on the similarity between the error patterns and the recognition result using the confidence score. The error-type classification model chooses the error type based on the most similar error pattern and the error frequency extracted from a learner corpus. The grammaticality checking method largely outperformed the two comparative models by 56.36% and 42.61% in F-score while keeping the false positive rate very low. The error-type classification model exhibited very high performance with a 99.6% accuracy rate. Because high precision and a low false positive rate are important criteria for the language-tutoring setting, the proposed method will be helpful for intelligent computer-assisted language learning systems.

On using intelligent computer-assisted language learning in real-life foreign language teaching and learning

AbstractThis paper explores the motivation and prerequisites for successful integration of Intelligent Computer-Assisted Language Learning (ICALL) tools into current foreign language teaching and learning (FLTL) practice. We focus on two aspects, which we argue to be important for effective ICALL system development and use: (i) the relationship between activity design and restrictions needed to make natural language processing tractable and reliable, and (ii) pedagogical considerations and the influence of activity design choices on the integration of ICALL systems into FLTL practice.

Developing an Intelligent Language Tutor

This article discusses the development and functionalities of an intelligent computer-assisted language learning (ICALL) system. By way of example, we describe E-Tutor, an ICALL system for L2 learners of German that has been in use for a decade. Based on advancements in technology, user studies with L2 learners of German as well as feedback provided by language instructors, students, and researchers, the system has undergone several system updates since its initial implementation in 1999. This article focuses on the pedagogical benefits of ICALL systems by also providing reflections on the development of such systems that resulted from the lessons we have learned in building and maintaining E-Tutor.

A balancing act: how can intelligent computer-generated feedback be provided in learner-to-learner interactions?

Task-based synchronous computer-mediated communication (CMC) may represent an optimal psycholinguistic environment for form-meaning connections, but learners do not receive feedback from a trusted authority. Intelligent computer-assisted language learning (ICALL) provides feedback, but the encouragement of communicative interaction remains largely unexplored. To combine the benefits of ICALL and CMC, we are designing a parser-based system that provides feedback on particle usage for first-year L2 Korean learners while they chat in CMC. Both to facilitate the use of a new orthography by beginning learners and to make processing feasible for the ICALL system, we guide the content of the activity by using picture-based information-gap tasks and a game record, and we control the range of allowable learner input by using a word bank. These constraints enable the system to address L2 errors in meaningful, goal-driven interactions.

A New KE-Free Online ICALL System Featuring Error Contingent Feedback

As a first step towards implementing a human language teacher, we have developed a new template-based on-line ICALL (intelligent computer assisted language learning) system capable of automatically diagnosing learners' free-format translated inputs and returning error contingent feedback. The system architecture we have adopted allows language teachers to build their own expertise into the system without the help of KEs (knowledge engineers), thus alleviating the long-standing KE bottlenecks associated with conventional expert-systems-based ITS (intelligent tutoring system) or ICALL (Murray, 1999). The core of the system comprises a unique FSA (finite state automaton)-based template knowledge base system, a robust and global HCS (heaviest common sequence)-based diagnostic engine, a POST(part-of speech-tagged) parser and related learners' model as well as an easy-to-use VTAT (visual template authoring tool). To simplify the task of authoring often quite complex template patterns, we have developed two sets of simpler rules; the first group of rules allows language teachers to manipulate complex sentence patterns with ease by constructing a template-template representation from which numerous separate templates can be extracted. The second group of buggy rules can be used to automatically generate syntactic bugs for learners by replacing part of the correct syntactic rules with plausible buggy rules. Using participants' responses extracted into the system templates, we present some convincing experimental verifications that the diagnostic engine is capable of providing error-contingent feedback and diagnosis applicable to a wide range of learners with differing educational backgrounds.

New Developments in Intelligent CALL Systems in a Rapidly Internationalized Information Age

With the advent of the rapidly spreading Internet accelerating the globalization of every sector of our community, the ICALL (Intelligent Computer-Assisted Language Learning) system has achieved remarkable advances at various fronts, notably in the integration of voice-enabling technology and human-computer-interface-related technology. This special issue on ICALL for the CALL journal presents an up-to-date account of recent developments in the ICALL system, which plays a vital role in advancing and stabilizing the global community in the information age.

Student modelling for second language acquisition

This paper describes the student model of an intelligent computer assisted language learning (ICALL) system which is based on current theories in the field of second language acquisition (SLA). The following four issues were selected as important questions in SLA, while also being implementable in the ICALL environment: (1) the acquisition order of the target rules; (2) language learning strategies; (3) language transfer; and (4) language awareness. The first three points are represented in the student model. A learner's language awareness is enhanced by explicit user-system discussion of these issues and the target constructions, and also by cooperative construction and repair of the student model. The project aims both to test the suitability of these theories in the context of ICALL, and at the same time develop a system which demonstrates guidelines for the creation of more successful and acceptable ICALL systems. The area of language used for illustration is clitic pronoun placement in European Portuguese.