Ming Che Lee

A novel sentence similarity measure for semantic-based expert systems

Research highlights? This research takes advantages of corpus-based ontology and Information Retrieval technologies to evaluate the semantic similarity between irregular sentences. ? The part of speech concept was taken into account and was integrated into the proposed semantic-VSM measure. ? This research tries to qualify the semantic similarity of natural language sentences. A novel sentence similarity measure for semantic based expert systems is presented. The well-known problem in the fields of semantic processing, such as QA systems, is to evaluate the semantic similarity between irregular sentences. This paper takes advantage of corpus-based ontology to overcome this problem. A transformed vector space model is introduced in this article. The proposed two-phase algorithm evaluates the semantic similarity for two or more sentences via a semantic vector space. The first phase built part-of-speech (POS) based subspaces by the raw data, and the latter carried out a cosine evaluation and adopted the WordNet ontology to construct the semantic vectors. Unlike other related researches that focused only on short sentences, our algorithm is applicable to short (4-5 words), medium (8-12 words), and even long sentences (over 12 words). The experiment demonstrates that the proposed algorithm has outstanding performance in handling long sentences with complex syntax. The significance of this research lies in the semantic similarity extraction of sentences, with arbitrary structures.

Integrating a semantic-based retrieval agent into case-based reasoning systems

This paper integrates techniques of natural language processing into a case retrieval agent.The use of semantic and syntactic information defines the meanings more accurately.Integrating semantic-based retrieval agent into the CBR system improves performance at initial state.The proposed CBR system with collaborative filtering constantly improves recommendation quality.The proposed CBR model outperforms the compared systems in the case study of an online bookstore. Natural language search engines should be developed to provide a friendly environment for business-to-consumer e-commerce that reduce the fatigue customers experience and help them decide what to buy. To support product information retrieval and reuse, this paper presents a novel framework for a case-based reasoning system that includes a collaborative filtering mechanism and a semantic-based case retrieval agent. Furthermore, the case retrieval agent integrates short-text semantic similarity (STSS) and recognizing textual entailment (RTE). The proposed approach was evaluated using competitive methods in the performance of STSS and RTE, and according to the results, the proposed approach outperforms most previously described approaches. Finally, the effectiveness of the proposed approach was investigated using a case study of an online bookstore, and according to the results of case study, the proposed approach outperforms a compared system using string similarity and an existing e-commerce system, Amazon.

A service-based framework for personalized learning objects retrieval and recommendation

With vigorous development of Internet, especially the web page interaction technology, distant e-learning has become more and more realistic and popular. To solve the problems of sharing and reusing teaching materials in different e-learning systems, presently several standard formats, including SCORM, IMS, LOM, and AICC, etc., have been proposed by several different international organizations. SCORM LOM, i.e. the Learning Object Metadata, enables the indexing and searching of learning objects in a learning object repository by extended sharing and searching features. However, LOM is deficient in semantic-awareness operations in spite of its multifarious fields in describing a Learning Object. It is difficult for a learner, even for advanced learners, to completely specify so many terms when they are searching. This paper proposes a service-based framework for personalized learning objects retrieval and recommendation. The work of personalization harnesses the power of probabilistic semantic inference for query keywords, LOM-based user preference logging, and other users’ feedback for recommendation weighting to retrieve the most suitable learning object for users. An ontology-based query expansion algorithm and an integrated learning objects recommendation algorithm are also proposed.

An Ontological Approach for Semantic Learning Objects Interoperability

This paper presents a semantic-aware classification algorithm that can leverage the interoperability among semantically heterogeneous learning object repositories using different ontologies. The proposed algorithm is to map sharable learning objects, using meanings instead of just keyword matching, from heterogeneous repositories into a local knowledge base (an e-learning ontology). Significance of this research lies in the semantic inferring rules for learning objects classification as well as the full automatic processing and self-optimizing capability. This approach is sufficiently generic to be embedded into other e-learning platforms for semantic interoperability among learning object repositories. Focused on digital learning material and contrasted to other traditional classification technologies, the proposed approach has experimentally demonstrated significantly improvement in performance.

An analysis of moodle in engineering education: The TAM perspective

Based on the Technology Acceptance Model (TAM) developed from the theory of reasoned action (TRA) and social psychology research by Davis (1989), this study models the use of the Internet-based modular object-oriented dynamic learning environment (Moodle) by students of the computer science department at Ming Chuan University (MCU), Taiwan. Apart from student demographics and background information (e.g., gender, frequency computer use, frequency Moodle use, etc.) that causes differences among TAM variables when using Moodle, the relationship between some additional external variables (e.g., system quality, reliability, interface design, interactivity, etc.) and TAM variables is investigated to provide suggestions for the application of information and computer education in science and engineering colleges, and to provide general information on using Internet-based teaching platforms. The participants of this study were undergraduate students of freshman, sophomore and junior from the computer science department at MCU, Taiwan. The questionnaires were distributed to a total of 260 students in six classes. 242 valid questionnaires were returned to give a valid rate of 0.93. The following observations are based on the questionnaires used in this study: 1) students have positive attitude toward using Moodle and have intention to use Moodle in the future; 2) system quality has less relationship with learning motivation but has medium influence on the attitude of students toward using Moodle; 3) “Attitude toward using” is highly correlated with “Behavioral intention to use”.

Effects of using self-explanation on a web-based Chinese sentence-learning system

Chinese as a foreign language (CFL) learners generally encounter difficulty in using some special rules of Chinese grammar because such grammar points do not exist in their native languages. CFL learners require an effective learning strategy to assist them in acquiring a greater understanding of Chinese grammar. Thus, we integrated a self-explanation strategy into a Chinese-learning system. Specifically, the system includes self-explanation prompts, instructional feedback, and remedial learning materials. The aim of this study was to determine the effects of using a self-explanation strategy on Chinese sentence learning in a computer-assisted language learning environment. The participants were assigned to an experiment group with self-explanation instruction and a control group without self-explanation to practice Chinese grammar points. Learning performance, including grammar tests and cognitive loads, was measured. The results showed higher learning outcomes for Chinese grammar and sentence structure in the self-explanation group. Furthermore, no significant difference in cognitive load was observed between the two groups. Implications for using self-explanation in computer-assisted language learning are discussed.

Meta-evaluation viewpoints on curriculum evaluation of engineering education: evidence from a north university of Taiwan

According to The Program Evaluation Standards (1994) published by The Joint Committee on Standards for Educational Evaluation (JCSEE), this study performs a meta-evaluation on the teaching feedback questionnaire (Appendix I) of Ming Chuan University (MCU), Taiwan, through questionnaire analysis in terms of the appropriateness and the indication of the questionnaire items. The participants of this study were first- to third-year undergraduate students from the computer science department at MCU, Taiwan. The questionnaires were distributed to a total of 231 anonymous students in six classes and 95% valid questionnaires were returned. The conclusions are as follows: 1) the attendance is highly related to conscientiousness and certainty; 2) conscientiousness is related to certainty at the significant level; 3) the teaching feedback questionnaire of MCU are not strongly representing the appropriateness and indication; and 4) teaching method and teaching effectiveness of appropriateness and indication are highly correlated.

A Discrete Particle Swarm Optimization Based Approach for Review Course Composition

In the present learning cycle, new knowledge learning and known knowledge review are two important learning processes. This paper proposes the review course composition system which adopts the discrete particle swarm optimization to quickly pick the suitable materials, and can be customized in accordance with the learners intention. As a result, such a composition system satisfies the majority of learners with the customized review courses based on their needs.