Browsing by Author "Chang, Tao-Hsing"

Now showing 1 - 12 of 12

An Unsupervised Automated Essay-Scoring System
(2010-09-01)
Chen, Yen-Yu
;
Liu, Chien-Liang
;
Lee, Chia-Hoang
;
Chang, Tao-Hsing
;
資訊工程學系
Automated Essay Scoring Using Set of Literary Sememes
(2009-03-01)
Chang, Tao-Hsing
;
Tsai, Pei-Yen
;
Lee, Chia-Hoang
;
Tam, Hak-Ping
;
資訊工程學系
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 literary 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.
Automated Essay Scoring Using Set of Literary Sememes
(2008)
Chang, Tao-Hsing
;
Lee, Chia-Hoang
;
Tsai, Pei-Yen
;
Tam, Hak-Ping
;
資訊工程學系
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.
Automatic Chinese Essay Scoring Using Connections between Concepts in Paragraphs
(2009)
Chang, Tao-Hsing
;
Lee, Chia-Hoang
;
資訊工程學系
;
Department of Computer Science
Automatic essay scoring (AES) system is a very important research tool for educational studies. Many studies indicate that current AES systems should be able to analyze semantic characteristics of an essay and include more such features to score essays. This study proposes a novel method which uses the similarity between the paragraphic conceptual connections in different essays to predict the scores of essays. Preliminary experiments show that the paragraphic conceptual structure in an essay can be an efficient feature for scoring the essay.
Clustering data with partial background information
(2019-05-01)
Liu, Chien-Liang
;
Hsaio, Wen-Hoar
;
Chang, Tao-Hsing
;
Li, Hsuan-Hsun
;
資訊工程學系
Clustering with partial supervision background information or semi-supervised clustering, learning from a combination of both labeled and unlabeled data, has received a lot of attention over the last decade. The supervisory information is usually used as the constraints to bias clustering towards a good region of search space. This paper proposes a semi-supervised algorithm, called constrained non-negative matrix factorization (Constrained-NMF), with a few labeled examples as constraints to improve performance. The proposed algorithm is a matrix factorization algorithm, in which initialization of matrices is required at the beginning. Although the benefits of good initialization are well-known, randomized seeding of basis matrix and coefficient matrix is still the standard approach for many non-negative matrix factorization (NMF) algorithms. This work devises an algorithm called entropy-based weighted semi-supervised fuzzy c-means (EWSS-FCM) algorithm to initialize the seeds. The experimental results indicate that the proposed Constrained-NMF can benefit from the initialization obtained from EWSS-FCM, which emphasizes the role of labeled examples and automatically weights them during the course of clustering. This work considers labeled examples in the objective functions to devise the two algorithms, in which the labeled information is propagated to unlabeled examples iteratively. We further analyze the proposed Constrained-NMF and give convergence justifications. The experiments are conducted on five real data sets, and experimental results indicate that the proposed algorithm generally outperforms the other alternatives.
Clustering documents with labeled and unlabeled documents using fuzzy semi-Kmeans
(2013-06-16)
Liu, Chien-Liang
;
Chang, Tao-Hsing
;
Li, Hsuan-Hsun
;
資訊工程學系
;
Department of Computer Science
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. (C) 2013 Elsevier B.V. All rights reserved.
Corpus-based Subtopic Segmentation Using Concept Segment Method
(2010-05-01)
Chang, Tao-Hsing
;
Lee, Chia-Hoang
;
Tam, Hak-Ping
;
資訊工程學系
;
Department of Computer Science
Many studies on topic segmentation have been launched in the past, but these previous methods performed poorly on domain-specific short texts. This paper will propose a method which employs high-level concepts on concept hierarchy to predict the number and location of subtopics in a short text, and then determine the boundary between subtopics using similarity measures. Experimental results show that the proposed method can greatly increase the accuracy of subtopic segmentation for domain-specific short texts.
Enhancing automatic Chinese essay scoring system from figures-of-speech
(2006-01-01)
Chang, Tao-Hsing
;
Lee, Chia-Hoang
;
Chang, Yu-Ming
;
資訊工程學系
;
Department of Computer Science
Chinese automated essay scoring (CAES) is a very important tool for many educational researches. However, none of the methods for retrieving features in English essays is applicable to Chinese writings because Chinese grammar parsers cannot produce reliable and useful syntactic features. CAES systems must explore other distinct features in Chinese writing. This paper proposes a method for retrieving two Chinese figures-of-speech from essays and to predict the scores of essays based on the two skills used in the essays. A scoring model based on ID3 decision tree algorithm will validate and show that the proposed method increases the performance of CAES effectively.
Locality Sensitive K-means Clustering
(2018-01-01)
Liu, Chlen-Liang
;
Hsai, Wen-Hoar
;
Chang, Tao-Hsing
;
資訊工程學系
;
工業工程與管理學系
This study considers clustering and dimensionality reduction simultaneously to devise an unsupervised clustering algorithm called locality sensitive K-means (LS-K means). The goal is to find a linear transformation to project data points into a lower dimensional space, so that clustering can perform well in the new space. We design a novel objective function for LS-Kmeans to achieve the goal, and further show that the proposed method can be reformulated as a matrix trace minimization with constraints problem. The original optimization problem becomes a generalized eigenvalue problem when relaxing the optimization problem of LS-Kmeans by allowing the indicator entries to take arbitrary values in R. This paper also shows that the continuous solutions for the transformed cluster membership indicator vectors of LS-Kmeans are located in the subspace spanned by the first K-1 eigenvectors. In the experiments, we use two synthetic datasets to show that the proposed method can cluster non-linearly separable data points. Besides, the experimental results of eight real datasets indicate that the proposed algorithm can generally outperform other alternatives.
Nonparametric multi-assignment clustering
(2017-01-01)
Liu, Chien-Liang
;
Hsaio, Wen-Hoar
;
Chang, Tao-Hsing
;
Jou, Tzai-Min
;
資訊工程學系
Multi-label learning has attracted significant attention from machine learning and data mining over the last decade. Although many multi-label classification algorithms have been devised, few research studies focus on multi-assignment clustering (MAC), in which a data instance can be assigned to multiple clusters. The MAC problem is practical in many application domains, such as document clustering, customer segmentation and image clustering. Additionally, specifying the number of clusters is always a difficult but critical problem for a certain class of clustering algorithms. Hence, this work proposes a non-parametric multi-assignment clustering algorithm called multi-assignment Chinese restaurant process (MACRP), which allows the model complexity to grow as more data instances are observed. The proposed algorithm determines the number of clusters from data, so it provides a practical model to process massive data sets. In the proposed algorithm, we devise a novel prior distribution based on the similarity graph to achieve the goal of multi-assignment, and propose a Gibbs sampling algorithm to carry out posterior inference. The implementation in this work uses collapsed Gibbs sampling and compares with several methods. Additionally, previous evaluation metrics used by multi-label classification are inappropriate for MAC, since label information is unavailable. This work further devises an evaluation metric for MAC based on the characteristics of clustering and multi-assignment problems. We conduct experiments on two real data sets, and the experimental results indicate that the proposed method is competitive and outperforms the alternatives on most data sets.
Semi-Supervised Text Classification With Universum Learning
(2016-02)
Liu, Chien-Liang
;
Hsaio, Wen-Hoar
;
Lee, Chia-Hoang
;
Chang, Tao-Hsing
;
Kuo, Tsung-Hsun
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.
Subtopic segmentation for small corpus using a novel fuzzy model
(2007-08-01)
Chang, Tao-Hsing
;
Lee, Chia-Hoang
;
資訊工程學系
;
Department of Computer Science
Subtopic segmentation is a critical task in numerous applications, including information retrieval, automatic summarization, essay scoring, and others. Although several approaches have been developed, many are ineffective for specific domains with a small corpus because of the fuzziness of the semantics of words and sentences in the corpus. This paper explores the problem of subtopic segmentation by proposing a fuzzy model for the semantics of both words and sentences. The model has three characteristics. First, it can deal with the uncertainty in the semantics of words and sentences. Secondly, it can measure the fuzzy similarity between the fuzzy semantics of sentences. Thirdly, it can develop a fuzzy algorithm for segmenting a text into several subtopic segments. The experiments, especially for a short text with a small corpus in a specific domain, indicate that the method can efficiently increase the accuracy of subtopic segmentation over previous methods.