This study examines the different patterns of online interaction between asynchronous communication and synchronous communication networks. Discussion transcripts were analyzed and coded using Bale’s Interaction Process Analysis (IPA) model (revised and expanded version). The preliminary findings showed significant differences in the interaction between social-emotional and task-oriented conten...

This paper rst gives a brief survey on current eeorts in language learning 1. Next, it presents a description of our learning system, an Adaptive Language Learner (AL Learner), for Context-Free Grammars (CFGs). This language learner is based on adaptation process, the EGLR parser serves as assimilation process and AL Learner serves as accomodation process. Then, an analysis on some complexity p...

This study identifies adult education program characteristics that predict improved learner outcomes through statistical analyses of data across four years in a single state. Data indicate that, collectively, several predictors contribute to our understanding of learner outcomes, including (a) learner entry level, (b) size of community, (c) staff qualifications, and (d) learner exposure to high...

Boosting is an ensemble based method which attempts to boost the accuracy of any given learning algorithm by applying it several times on slightly modi ed training data and then combining the results in a suitable manner. The boosting algorithms that we covered in class were AdaBoost, LPBoost, TotalBoost, SoftBoost, and Entropy Regularized LPBoost. The basic idea behind these boosting algorithm...

Human tutors, in dealing with non-native speakers, draw from their knowledge of common learner mistakes to understand learner speech and offer effective corrective advice. In this paper we present our work towards embedding some of this knowledge in the speech recognition and learner speech error detection subsystems of the Tactical Language Training System (TLTS). We discuss the implementation...

We introduce a formal model of teaching in which the teacher is tailored to a particular learner, yet the teaching protocol is designed so that no collusion is possible. Not surprisingly, such a model remedies the non-intuitive aspects of otehr models in which the teacher must successfully teach any consistent learner. We prove that any class that can be exactly identified by a deterministic po...

Stability has been explored to study the performance of learning algorithms in recent years and it has been shown that stability is sufficient for generalization and is sufficient and necessary for consistency of ERM in the general learning setting. Previous studies showed that AdaBoost has almost-everywhere uniform stability if the base learner has L1 stability. The L1 stability, however, is t...

No learner is generally better than another learner. If a learner performs better than another learner on some learning situations, then the first learner usually performs worse than the second learner on other situations. In other words, no single learning algorithm can perform well and uniformly outperform other algorithms over all learning or data mining tasks. There is an increasing number ...

This paper presents a brief review of early learner modelling in Intelligent Tutoring Systems focusing particularly on procedural knowledge representations vs. declarative knowledge representations. It then tracks the paradigm shift from traditional learner modelling, which emphasises knowledge representation, to distributed learner modelling, which focuses on the modelling process. Learner mod...