Little Things With Big Effects: On the Identification and Interpretation of Tokens for Error Diagnosis in ICALL
نویسندگان
چکیده
Intelligent Computer-Assisted Language Learning (ICALL) systems differentiate themselves from traditional CALL systems through their ability to analyze learner input. They can identify language properties and diagnose errors, which in principle allows ICALL systems to provide specific, individualized feedback for a wider range of learner input and activity types. Error diagnosis can be conceived as a process abstracting from the learner’s production to a set of linguistic features that best describe the learner’s (mis)conceptions of the linguistic structures represented in a given input string.1 This process may comprise several steps that take into consideration morphological, syntactic, and semantic properties of the input. However, it almost invariably starts with the identification of the basic linguistic units that will serve as the building blocks of the analysis, i.e., the identification and interpretation of tokens. In this paper, we discuss the identification and interpretation of tokens and the mismatches that can arise in an ICALL context between the learner’s conceptualization of a given token and the system’s interpretation of its linguistic properties. The general issue is made concrete using real-life examples from the error diagnosis performed by TAGARELA, an ICALL system for Portuguese. We tested the system with students from introductory Portuguese courses at the Ohio State University in Spring 2007. Analyzing the logs which record what the students
منابع مشابه
Estimation of parameters of metal-oxide surge arrester models using Big Bang-Big Crunch and Hybrid Big Bang-Big Crunch algorithms
Metal oxide surge arrester accurate modeling and its parameter identification are very important for insulation coordination studies, arrester allocation and system reliability. Since quality and reliability of lightning performance studies can be improved with the more efficient representation of the arresters´ dynamic behavior. In this paper, Big Bang – Big Crunch and Hybrid Big Bang – Big Cr...
متن کاملBayesian Modeling Based on Data from the Internet of Things
The Internet of Things is suggested as the upcoming revolution in the Information and communication technology due to its very high capability of making various businesses and industries more productive and efficient. This productivity comes from the emergence of innovation and the introduction of new capabilities for businesses. Different industries have shown varying reactions to IOT, but wha...
متن کاملEstimating the Parameters for Linking Unstandardized References with the Matrix Comparator
This paper discusses recent research on methods for estimating configuration parameters for the Matrix Comparator used for linking unstandardized or heterogeneously standardized references. The matrix comparator computes the aggregate similarity between the tokens (words) in a pair of references. The two most critical parameters for the matrix comparator for obtaining the best linking results a...
متن کاملSurvey and Effects of Manufacture and Assembly Errors on the Output Error of Globoidal Cam Mechanisms
The output error of the globoidal cam mechanism can be considered as a relevant indicator of mechanism performance, because it determines kinematic and dynamical behavior of mechanical transmission. Based on the differential geometry and the rigid body transformations, the mathematical model of surface geometry of the globoidal cam is established. Then we present the analytical expression of th...
متن کامل