Isamu Shioya

Topic Detection and Tracking for News Web Pages

This paper proposes a new approach to observe, summarize and track events from a collection of news Web pages. Given a set of temporal Web pages, we obtain valid times-tamp from Web pages and detect events by means of clustering. Then we track events by using KeyGraph based on the clusters and abstract the clusters by using SuffixTree. We examine some experimental results and show the usefulness of our approach

Mining Type Schemes in Databases

We propose a heuristic method to mine type scheme semiautomatically from initial database scheme and the instances. Unlike conventional database design methods, the proposed one starts from examining database entities.

Knowledge acquisition for classification systems

We propose a new method to mine a type scheme semi-automatically from an initial database scheme and the instances. Our data model assumes that one entity may have more than one type and classification (or type scheme). It might be appropriate when each entity is classified into at most k (least general) classes with respect to the ISA hierarchy, to keep database processing efficient. Our method differs from others in evolving ISA hierarchy by introducing a semantical metric. We propose a sophisticated algorithm to simplify, evolve and generate type schemes.

Improving text categorization by resolving semantic ambiguity

In this investigation, we propose a new method for text categorization (TC) based on Bayesian approach by resolving ambiguity. The TC assumes weights to words of which meanings are ambiguous in a sense of synonymy and polysemy. We give weights to articles by examining dictionaries of thesaurus and of dimensionality reduction to improve the quality of TC. Also we show some experiments to illustrate how well our approach goes.

Similarity among melodies for music information retrieval

Here we discuss how to look for similar melody in music databases by giving monophonic melody in sheet. In this work, we utilize text expression (or sheet music) to describe music and introduce pitch spectrum of melodies. By this feature, we concisely distinguish music from tempo, transposition or other arbitrary expressions. We show the usefulness by experimental results.

Meta model approach for mediation

In this work, we discuss how to interpret traditional Data Flow Diagram (DFD) by Unified Modeling Language (UML) for the purpose of integrating legacy systems with modern systems. To do that we introduce DFD meta model by using UML class diagrams and Object Constraint Language (OCL). We utilize the meta model to capture DFD semantics and establish close correspondence between DFD expressions and the expressions that can be derived by instantiating the meta framework. At the same time we describe procedures to generate UML descriptions from DFD based on the correspondence.

Giving temporal order to news corpus

We propose a new mechanism to give temporal order to a news article in a form of times-tamps. Here we learn temporal data in advance to extract ordering by means of incremental clustering and then we estimate most likely order to news text. In this work, we examine TDT2 corpus and we show how well our approach works by some experiments.

Classifying News Corpus by self-organizing maps

In this paper, we introduce extended self organization map (SOM), called k-propagated SOM (K-SOM, or SOM(k)), and discuss how to classify text documents. Also we discuss how we evaluate classification capabilities of points on SOM (K-SOM) maps. We discuss some experiments to Reuters News Corpus datasets and show the usefulness of K-SOM.

Knowledge pruning in decision trees

We propose a novel pruning method of decision trees based on domain knowledge, semantic hierarchies among classes, which is used to generate decision trees by relaxing the levels of hierarchies for both height and width of the trees. We develop the algorithm, and the effectiveness is examined by UCI Machine Learning Repository: On Car Evaluation and Nursery. We can generate the decision trees consisting of 11 and 13 rules, although C4.5 generates 182 and 572 rules, respectively.

Estimating The Date of Blog Authors by CRF

In this investigation, we propose a sophisticated approach for estimating the ages of blog authors by means of stochastic process. In this technique, we give weights on every word appeared in training data, and we extract a collection of feature words to each age. Then we examine articles on Blog based on the feature information and estimate the age by obtaining label to each word by means of conditional random fields (CRF). We show the effectiveness of our approach by some experiments.