Tao-Hsing Chang

Finding multiple possible critical paths using fuzzy PERT

Program evaluation and review techniques (PERT) is an efficient tool for large project management. In actual project control decisions, PERT has successfully been applied to business management, industry production, project scheduling control, logistics support, etc. However, classical PERT requires a crisp duration time representation for each activity. This requirement is often difficult for the decision-makers due to the fact that they usually can not estimate these values precisely. In recent years, some fuzzy PERT methods have been proposed based on fuzzy set theory for project management. However, there is a drawback in the existing fuzzy PERT methods, i.e., sometimes they maybe cannot find a critical path in a fuzzy project network. In this paper, we propose a fuzzy PERT algorithm to find multiple possible critical paths in a fuzzy project network, where the duration time of each activity in a fuzzy project network is represented by a fuzzy number. The proposed algorithm can overcome the drawback of the existing fuzzy PERT methods.

Supporting teachers' reflection and learning through structured digital teaching portfolios

Digital teaching portfolios have been proposed as an effective tool for teacher learning and professional development, but there is a lack of empirical evidence supporting their effectiveness. This study proposed the design of a structured digital portfolio equipped with multiple aids (e.g. self-assessment, peer assessment, discussion and journal writing) for the professional development of teachers. This study also empirically evaluated the reflection and professional development as demonstrated in digital teaching portfolios with multiple supporting measures. Fourty-four in-service substitute teachers participated in a course of classroom assessment and used a web-based portfolio system. Based on the framework of teacher reflective thinking developed by Sparks-Langer et al., we found that most teachers demonstrated moderate levels of reflection in their journals but only one-third of them showed the highest level of reflection. We also found that the professional knowledge of teachers about classroom assessment - as shown by their implementation of it - improved significantly during the construction of portfolios. The above findings also represent good evidence that digital portfolios with multiple aids are beneficial to teacher reflection and professional development.

An Unsupervised Automated Essay Scoring System

The proposed automated essay-scoring system uses an unsupervised-learning approach based on a voting algorithm. Experiments show that this approach works well compared to supervised-learning approaches.

Semi-Supervised Text Classification With Universum Learning

Universum, a collection of nonexamples that do not belong to any class of interest, has become a new research topic in machine learning. This paper devises a semi-supervised learning with Universum algorithm based on boosting technique, and focuses on situations where only a few labeled examples are available. We also show that the training error of AdaBoost with Universum is bounded by the product of normalization factor, and the training error drops exponentially fast when each weak classifier is slightly better than random guessing. Finally, the experiments use four data sets with several combinations. Experimental results indicate that the proposed algorithm can benefit from Universum examples and outperform several alternative methods, particularly when insufficient labeled examples are available. When the number of labeled examples is insufficient to estimate the parameters of classification functions, the Universum can be used to approximate the prior distribution of the classification functions. The experimental results can be explained using the concept of Universum introduced by Vapnik, that is, Universum examples implicitly specify a prior distribution on the set of classification functions.

Clustering documents with labeled and unlabeled documents using fuzzy semi-Kmeans

While focusing on document clustering, this work presents a fuzzy semi-supervised clustering algorithm called fuzzy semi-Kmeans. The fuzzy semi-Kmeans is an extension of K-means clustering model, and it is inspired by an EM algorithm and a Gaussian mixture model. Additionally, the fuzzy semi-Kmeans provides the flexibility to employ different fuzzy membership functions to measure the distance between data. This work employs Gaussian weighting function to conduct experiments, but cosine similarity function can be used as well. This work conducts experiments on three data sets and compares fuzzy semi-Kmeans with several methods. The experimental results indicate that fuzzy semi-Kmeans can generally outperform the other methods.

Automatic Chinese unknown word extraction using small-corpus-based method

Chinese unknown word extraction is an important problem for Chinese language processing. There are troublesome difficulties in the problem. First, almost any Chinese character can either represent a word or be a part of other words. Secondly, there is no blank between Chinese words for identifying the boundaries. Although some approaches have been proposed, there are some drawbacks in these methods. Here, we present and develop a method to extract Chinese unknown words more efficiently and precisely. It retains efficiency and accuracy even though the size of document set is small for training. It can also extract the unknown words occur rarely. Based on these advantages, it is very practical for real applications.

The effect of online summary assessment and feedback system on the summary writing on 6th graders: The LSA-based technique

Abstract Studies on teaching of reading strategies have found that summarizing is of tremendous help to reading comprehension. However grading students’ summary writings is laborious, but given the importance of summarizing, an effective summarizing learning module is important. This study developed an automatic summary assessment and feedback system based on Latent Semantic Analysis (LSA) to provide score, concept and semantic feedback, and then investigated the effects of concept and semantic feedback on the writing of summaries by students in the sixth grade. The design involved two between-subject factors: semantic feedback (with, without) and concept feedback (with, without). 120 sixth-grade students from an elementary school were recruited for the study, and then were randomly assigned to each group. The overall results demonstrated the effectiveness of the proposed system in improving the summary writing skills of students. The effects of semantic feedback and concept feedback were also discussed.

Constructing and validating readability models: the method of integrating multilevel linguistic features with machine learning

Multilevel linguistic features have been proposed for discourse analysis, but there have been few applications of multilevel linguistic features to readability models and also few validations of such models. Most traditional readability formulae are based on generalized linear models (GLMs; e.g., discriminant analysis and multiple regression), but these models have to comply with certain statistical assumptions about data properties and include all of the data in formulae construction without pruning the outliers in advance. The use of such readability formulae tends to produce a low text classification accuracy, while using a support vector machine (SVM) in machine learning can enhance the classification outcome. The present study constructed readability models by integrating multilevel linguistic features with SVM, which is more appropriate for text classification. Taking the Chinese language as an example, this study developed 31 linguistic features as the predicting variables at the word, semantic, syntax, and cohesion levels, with grade levels of texts as the criterion variable. The study compared four types of readability models by integrating unilevel and multilevel linguistic features with GLMs and an SVM. The results indicate that adopting a multilevel approach in readability analysis provides a better representation of the complexities of both texts and the reading comprehension process.

Automated essay scoring using set of literary sememes

Automatic essay scoring system is a very important research tool for many educational studies. Many researches indicate that AES systems should be able to analyze semantic characteristics of an essay and include more such features to score essays. This paper makes an assumption: some concepts that can be regarded as literary concepts would only be utilized by skillful writers. However, it is a difficult task to extract literal concepts due to small size of training corpora. This work uses a semantic network tool to overcome the problem. The concepts in essays can be transformed into sememes using the tool and literary concepts are also transformed into literary sememes. This work introduces a method which makes use of the literary sememes in an essay to score the essay. Experimental results show that the accuracy of the proposed method for Chinese essays is comparable to those as achieved by several current English AES systems.

Constructing a Novel Chinese Readability Classification Model Using Principal Component Analysis and Genetic Programming

The studies of readability aim to measure the level of text difficulty. Although traditional formulae such as the Flesch-Kincaid formula can properly predict text readability, they are only effective for English text. Other formulae with very few features may result in inaccurate text classification. The study takes into account multiple linguistic features, and attempts to increase the level of accuracy in text classification by adopting a new model which integrates Principal Component Analysis (PCA) with Genetic Programming (GP). Empirical data are utilized to demonstrate the performance of the proposed model.