Hao Ren Ke

Text summarization using a trainable summarizer and latent semantic analysis

This paper proposes two approaches to address text summarization: modified corpus-based approach (MCBA) and LSA-based T.R.M. approach (LSA + T.R.M.). The first is a trainable summarizer, which takes into account several features, including position, positive keyword, negative keyword, centrality, and the resemblance to the title, to generate summaries. Two new ideas are exploited: (1) sentence positions are ranked to emphasize the significances of different sentence positions, and (2) the score function is trained by the genetic algorithm (GA) to obtain a suitable combination of feature weights. The second uses latent semantic analysis (LSA) to derive the semantic matrix of a document or a corpus and uses semantic sentence representation to construct a semantic text relationship map. We evaluate LSA + T.R.M. both with single documents and at the corpus level to investigate the competence of LSA in text summarization. The two novel approaches were measured at several compression rates on a data corpus composed of 100 political articles. When the compression rate was 30%, an average f-measure of 49% for MCBA, 52% for MCBA + GA, 44% and 40% for LSA + T.R.M. in single-document and corpus level were achieved respectively.

Exploring behavior of E-journal users in science and technology: Transaction log analysis of Elsevier's ScienceDirect OnSite in Taiwan

In the era of digital libraries, Web-based electronic databases have become important resources for education and research, providing functionality and ease of use superior to print products. Analysis of usage of such online systems can provide valuable information on user behavior, and on usage of electronic information in general. Furthermore, the findings can be used to improve effectiveness of these electronic systems and identify areas for improvement, ranging from user interface and functionality to documentation and product training. This article analyzes usage of the Taiwan-based ScienceDirect OnSite E-journal system, one of the largest and most heavily used full-text Science, Technology, and Medicine (STM) databases worldwide.

Classifier design with feature selection and feature extraction using layered genetic programming

This paper proposes a novel method called FLGP to construct a classifier device of capability in feature selection and feature extraction. FLGP is developed with layered genetic programming that is a kind of the multiple-population genetic programming. Populations advance to an optimal discriminant function to divide data into two classes. Two methods of feature selection are proposed. New features extracted by certain layer are used to be the training set of next layers populations. Experiments on several well-known datasets are made to demonstrate performance of FLGP.

Designing a classifier by a layered multi-population genetic programming approach

This paper proposes a method called layered genetic programming (LAGEP) to construct a classifier based on multi-population genetic programming (MGP). LAGEP employs layer architecture to arrange multiple populations. A layer is composed of a number of populations. The results of populations are discriminant functions. These functions transform the training set to construct a new training set. The successive layer uses the new training set to obtain better discriminant functions. Moreover, because the functions generated by each layer will be composed to a long discriminant function, which is the result of LAGEP, every layer can evolve with short individuals. For each population, we propose an adaptive mutation rate tuning method to increase the mutation rate based on fitness values and remaining generations. Several experiments are conducted with different settings of LAGEP and several real-world medical problems. Experiment results show that LAGEP achieves comparable accuracy to single population GP in much less time.

iSpreadRank: Ranking sentences for extraction-based summarization using feature weight propagation in the sentence similarity network

Sentence extraction is a widely adopted text summarization technique where the most important sentences are extracted from document(s) and presented as a summary. The first step towards sentence extraction is to rank sentences in order of importance as in the summary. This paper proposes a novel graph-based ranking method, iSpreadRank, to perform this task. iSpreadRank models a set of topic-related documents into a sentence similarity network. Based on such a network model, iSpreadRank exploits the spreading activation theory to formulate a general concept from social network analysis: the importance of a node in a network (i.e., a sentence in this paper) is determined not only by the number of nodes to which it connects, but also by the importance of its connected nodes. The algorithm recursively re-weights the importance of sentences by spreading their sentence-specific feature scores throughout the network to adjust the importance of other sentences. Consequently, a ranking of sentences indicating the relative importance of sentences is reasoned. This paper also develops an approach to produce a generic extractive summary according to the inferred sentence ranking. The proposed summarization method is evaluated using the DUC 2004 data set, and found to perform well. Experimental results show that the proposed method obtains a ROUGE-1 score of 0.38068, which represents a slight difference of 0.00156, when compared with the best participant in the DUC 2004 evaluation.

Knowledge‐based mobile learning framework for museums

Purpose – The purpose of this study is to propose a knowledge‐based mobile learning framework that integrates various types of museum‐wide content, and supports ubiquitous, context‐aware, personalized learning for museums.Design/methodology/approach – A unified knowledge base with multi‐layer reusable content structures serves as the kernel component to integrate content from exhibitions for education and collection in a museum. The How‐Net approach is adopted to build a unified natural and cultural ontology. The ontology functions as a common and sharable knowledge concept that denotes each knowledge element in the unified knowledge base, and associates each learners learning context and usage with a content and usage profile respectively. Data mining algorithms, e.g. association mining and clustering, are applied to discover useful patterns for ubiquitous personalization from these content and usage profiles.Findings – A pilot project based on the proposed framework has been successfully implemented in...

Design and performance evaluation of mobile web services in libraries: A case study of the Oriental Institute of Technology Library

Purpose – This research aims to use the Oriental Institute of Technology Library (the OIT Library) in Taiwan as a case to introduce some of the mobile web services which can be provided by a library, as well as to investigate and discuss the first two mobile web services offered by the OIT Library, the due‐day reminder and renewal‐request services, at length. Furthermore, the performance evaluation of the two services is conducted.Design/methodology/approach – This research employs system logs and patron questionnaires to understand the effectiveness of, and patron satisfaction toward, the two services.Findings – Results of system log analysis show that the usage of the two services improves the average number of overdue occurrences, average amount of overdue fines, average amount of overdue fines per transaction, and average overdue rate; furthermore, the use of the services also indirectly increases the number of items borrowed by patrons, which corresponds with the questionnaire analysis as well. Resul...

Structure clustering for Chinese patent documents

This paper aims to cluster Chinese patent documents with the structures. Both the explicit and implicit structures are analyzed to represent by the proposed structure expression. Accordingly, an unsupervised clustering algorithm called structured self-organizing map (SOM) is adopted to cluster Chinese patent documents with both similar content and structure. Structured SOM clusters the similar content of each sub-part structure, and then propagates the similarity to upper level ones. Experimental result showed the maps size and number of patents are proportional to the computing time, which implies the width and depth of structure affects the performance of structured SOM. Structured clustering of patents is helpful in many applications. In the lawsuit of copyright, companies are easy to find claim conflict in the existent patents to contradict the accusation. Moreover, decision-maker of a company can be advised to avoid hot-spot aspects of patents, which can save a lot of R&D effort.

A two-level relevance feedback mechanism for image retrieval

Content-based image retrieval (CBIR) is a group of techniques that analyzes the visual features (such as color, shape, texture) of an example image or image subregion to find similar images in an image database. Relevance feedback is often used in a CBIR system to help users express their preference and improve query results. Traditional relevance feedback relies on positive and negative examples to reformulate the query. Furthermore, if the system employs several visual features for a query, the weight of each feature is adjusted manually by the user or system predetermined and fixed by the system. In this paper we propose a new relevance feedback model suitable for medical image retrieval. The proposed method enables the user to rank the results in relevance order. According to the ranking, the system can automatically determine the importance ranking of features, and use this ranking to automatically adjust the weight of each feature. The experimental results show that the new relevance feedback mechanism outperforms previous relevance feedback models.

Chinese Text Summarization Using a Trainable Summarizer and Latent Semantic Analysis

In this paper, two novel approaches are proposed to extract important sentences from a document to create its summary. The first is a corpus-based approach using feature analysis. It brings up three new ideas: 1) to employ ranked position to emphasize the significance of sentence position, 2) to reshape word unit to achieve higher accuracy of keyword importance, and 3) to train a score function by the genetic algorithm for obtaining a suitable combination of feature weights. The second approach combines the ideas of latent semantic analysis and text relationship maps to interpret conceptual structures of a document. Both approaches are applied to Chinese text summarization. The two approaches were evaluated by using a data corpus composed of 100 articles about politics from New Taiwan Weekly, and when the compression ratio was 30%, average recalls of 52.0% and 45.6% were achieved respectively.