Jie-Chi Yang

Wireless and mobile technologies to enhance teaching and learning

This research aims to build a Wireless Technology Enhanced Classroom (WiTEC) that supports everyday activities unobtrusively and seamlessly in classroom contexts. This paper describes the integration of wireless LAN, wireless mobile learning devices, an electronic whiteboard, an interactive classroom server, and a resource and class management server to build the WiTEC. This contains a number of features that can support class members in various types of teaching and learning activities. Project-based learning is taken as a scenario to elaborate how teachers and students can engage in teaching and learning via WiTEC. Finally, a number of suggestions are discussed for further study.

Affordances of mobile technologies for experiential learning: the interplay of technology and pedagogical practices

Experiential learning is the process of creating knowledge through the transformation of experience and has been adopted in an increasing number of areas. This paper investigates the possibility of technological support for experiential learning. A learning activity flow (or script) and a mobile technology system were designed to facilitate students in experiential learning. An experiment was conducted on two fifth-grade classes at an elementary school, one class using personal digital assistants (PDAs) and the other working without them. The results indicate that mobile technologies are effective in improving knowledge creation during experiential learning. The interplay between the mobile technology affordances and the proposed learning flow for experiential learning is thoroughly discussed.

Robust and efficient multiclass SVM models for phrase pattern recognition

Phrase pattern recognition (phrase chunking) refers to automatic approaches for identifying predefined phrase structures in a stream of text. Support vector machines (SVMs)-based methods had shown excellent performance in many sequential text pattern recognition tasks such as protein name finding, and noun phrase (NP)-chunking. Even though they yield very accurate results, they are not efficient for online applications, which need to handle hundreds of thousand words in a limited time. In this paper, we firstly re-examine five typical multiclass SVM methods and the adaptation to phrase chunking. However, most of them were inefficient when the number of phrase types scales. We thus introduce the proposed two new multiclass SVM models that make the system substantially faster in terms of training and testing while keeps the SVM accurate. The two methods can also be applied to similar tasks such as named entity recognition and Chinese word segmentation. Experiments on CoNLL-2000 chunking and Chinese base-chunking tasks showed that our method can achieve very competitive accuracy and at least 100 times faster than the state-of-the-art SVM-based phrase chunking method. Besides, the computational time complexity and the time cost analysis of our methods were also given in this paper.

Development and evaluation of multiple competitive activities in a synchronous quiz game system

Competitive learning activities are among the various learning activities that play a significant role in online learning environments. A competitive learning environment obviously stimulates different feelings in winners and losers, and it is imperative to consider how to design such an environment so as to motivate users. This work describes the design of an online competitive learning environment that involves three basic competitive forms and 16 competitive activities. A system called ‘Joyce’ has been implemented, in which users can compete with either a computer agent or real life user(s) on a single computer or alternatively can play via the Internet. Because of the format of the item bank being sets of multiple-choice questions, the system is not restricted by the age of its target users. In a game-learning environment, learning is a side-effect of participating in the game. In the present example, learners are motivated to read more materials to win the game. The system attempts to involve students in a competitive gaming-learning environment that stimulated their motivation to learn. Three studies have been conducted to examine how users responded to the novel system and obtained the following analytical results: first, users were found to be highly motivated to use the Joyce system; second, more able users had a greater chance of winning the game, while less able users still had some chance of winning; and third, users are inclined to take risks and have the control of the game in their own hands.

A support vector machine-based context-ranking model for question answering

Modern information technologies and Internet services are suffering from the problem of selecting and managing a growing amount of textual information, to which access is often critical. Machine learning techniques have recently shown excellent performance and flexibility in many applications, such as artificial intelligence and pattern recognition. Question answering (QA) is a method of locating exact answer sentences from vast document collections. This paper presents a machine learning-based question-answering framework, which integrates a question classifier, simple document/passage retrievers, and the proposed context-ranking models. The question classifier is trained to categorize the answer type of the given question and instructs the context-ranking model to re-rank the passages retrieved from the initial retrievers. This method provides flexible features to learners, such as word forms, syntactic features, and semantic word features. The proposed context-ranking model, which is based on the sequential labeling of tasks, combines rich features to predict whether the input passage is relevant to the question type. We employ TREC-QA tracks and question classification benchmarks to evaluate the proposed method. The experimental results show that the question classifier achieves 85.60% accuracy without any additional semantic or syntactic taggers, and reached 88.60% after we employed the proposed term expansion techniques and a predefined related-word set. In the TREC-10 QA task, by using the gold TREC-provided relevant document set, the QA model achieves a 0.563 mean reciprocal rank (MRR) score, and a 0.342 MRR score is achieved after using the simple document and passage retrieval algorithms.

Testing learner reliance on caption supports in second language listening comprehension multimedia environments

Listening comprehension in a second language (L2) is a complex and particularly challenging task for learners. Because of this, L2 learners and instructors alike employ different learning supports as assistance. Captions in multimedia instruction readily provide support and thus have been an ever-increasing focus of many studies. However, captions must eventually be removed, as the goal of language learning is participation in the target language where captions are not typically available. Consequently, this creates a dilemma particularly for language instructors as to the usage of captioning supports, as early removal may cause frustration, while late removal may create learning interference. Accordingly, the goal of the current study was to propose and employ a testing instrument, the Caption Reliance Test (CRT), which evaluates individual learners’ reliance on captioning in second language learning environments; giving a clear indication of the learners’ reliance on captioning, mirroring their support needs. Thus, the CRT was constructed comprised of an auditory track, accompanied by congruent textual captions, as well as particular incongruent textual words, to provide a means for testing. It was subsequently employed in an empirical study involving English as a Foreign Language (EFL) high school students. The results exhibited individual variances in the degree of reliance and, more importantly, exposed a negative correlation between caption reliance and L2 achievement. In other words, learners’ reliance on captions varies individually and lower-level achievers rely on captions for listening comprehension more than their high-level counterparts, indicating that learners at various comprehension levels require different degrees of caption support. Thus, through employment of the CRT, instructors are able to evaluate the degree to which learners rely on the caption supports and thus make informed decisions regarding learners’ requirements and utilization of captions as a multimedia learning support.

Captions and reduced forms instruction: The impact on EFL students’ listening comprehension

For many EFL learners, listening poses a grave challenge. The difficulty in segmenting a stream of speech and limited capacity in short-term memory are common weaknesses for language learners. Specifically, reduced forms, which frequently appear in authentic informal conversations, compound the challenges in listening comprehension. Numerous interventions have been implemented to assist EFL language learners, and of these, the application of captions has been found highly effective in promoting learning. Few studies have examined how different modes of captions may enhance listening comprehension. This study proposes three modes of captions: full, keyword-only, and annotated keyword captions and investigates their contribution to the learning of reduced forms and overall listening comprehension. Forty-four EFL university students participated in the study and were randomly assigned to one of the three groups. The results revealed that all three groups exhibited improvement on the pre-test while the annotated keyword caption group exhibited the best performance with the highest mean score. Comparing performances between groups, the annotated keyword caption group also emulated both the full caption and the keyword-only caption groups, particularly in the ability to recognize reduced forms. The study sheds light on the potential of annotated keyword captions in enhancing reduced forms learning and overall listening comprehension.

A Robust Passage Retrieval Algorithm for Video Question Answering

In this paper, we present a robust passage retrieval algorithm to extend the conventional text question answering (Q/A) to videos. Users interact with our videoQ/A system through natural language queries, while the top-ranked passage fragments with associated video clips are returned as answers. We compare our method with five of the high-performance ranking algorithms that are portable to different languages and domains. The experiments were evaluated with 75.3 h of Chinese videos and 253 questions. The experimental results showed that our method outperformed the second best retrieval model (language models) in relatively 1.43% in mean reciprocal rank (MRR) score and 11.36% when employing a Chinese word segmentation tool. By adopting the initial retrieval results from the retrieval models, our method yields an improvement of at least 5.94% improvement in MRR score. This makes it very attractive for the Asia-like languages since the use of a well-developed word tokenizer is unnecessary.

EduXs: multilayer educational services platforms

How to use the online social learning communities to improve quality and quantity of interactions in physical social learning communities is an important issue. This work describes the design and implementation of multilayer educational services platforms that enable learners to establish their own online social learning communities and integrate their online social learning communities into a large public social learning portal site--EduCities. Multilayer educational services platforms were designed to integrate various individual online social learning communities, and to map these communities into physical social learning communities. This work proposes and implements an architecture called EduXs, and integrates it with K-12 social learning communities. One year after the EduXs system was released on the Internet, 1,849 schools, 15,772 classes, and 130,908 individuals in Taiwan had registered to use the system to construct their own online social learning communities. Among these registered users, 18.8% of registered schools, and 24.7% of registered classes continue to use the system. Evaluation results indicate that the system is accepted by teachers and students.

An Approximate Approach for Training Polynomial Kernel SVMs in Linear Time

Kernel methods such as support vector machines (SVMs) have attracted a great deal of popularity in the machine learning and natural language processing (NLP) communities. Polynomial kernel SVMs showed very competitive accuracy in many NLP problems, like part-of-speech tagging and chunking. However, these methods are usually too inefficient to be applied to large dataset and real time purpose. In this paper, we propose an approximate method to analogy polynomial kernel with efficient data mining approaches. To prevent exponential-scaled testing time complexity, we also present a new method for speeding up SVM classifying which does independent to the polynomial degree d. The experimental results showed that our method is 16.94 and 450 times faster than traditional polynomial kernel in terms of training and testing respectively.