Myunggwon Hwang

Automatic Enrichment of Semantic Relation Network and Its Application to Word Sense Disambiguation

The most fundamental step in semantic information processing (SIP) is to construct knowledge base (KB) at the human level; that is to the general understanding and conception of human knowledge. WordNet has been built to be the most systematic and as close to the human level and is being applied actively in various works. In one of our previous research, we found that a semantic gap exists between concept pairs of WordNet and those of real world. This paper contains a study on the enrichment method to build a KB. We describe the methods and the results for the automatic enrichment of the semantic relation network. A rule based method using WordNets glossaries and an inference method using axioms for WordNet relations are applied for the enrichment and an enriched WordNet (E-WordNet) is built as the result. Our experimental results substantiate the usefulness of E-WordNet. An evaluation by comparison with the human level is attempted. Moreover, WSD-SemNet, a new word sense disambiguation (WSD) method in which E-WordNet is applied, is proposed and evaluated by comparing it with the state-of-the-art algorithm.

Technology trends analysis and forecasting application based on decision tree and statistical feature analysis

Analyzing mass information and supporting foresight are very important task but they are extremely time-consuming work. In addition, information analysis and forecasting about the science and technology are also very critical tasks for researchers, government officers, businessman, etc. Some related studies recently have been executed and semi-automatic tools have been developed actively. Many researchers, annalists, and businessmen also generally use those tools for strategic decision making. However, existing projects and tools are based on subjective opinions from several experts and most of tools simply explain current situations, not forecasting near future trends. Therefore, in this paper, we propose a technology trends analysis and forecasting model based on quantitative analysis and several text mining technologies for effective, systematic, and objective information analysis and forecasting technology trends. Additionally, we execute a comparative evaluation between the suggested model and Gartners forecasting model for validating the suggested model because the Gartners model is widely and generally used for information analysis and forecasting.

Prescriptive Analytics System for Improving Research Power

We introduce a prescriptive analytics system, InSciTe advisory, to provide researchers with advice of their future research direction and strategy. The system analyzes several thousands of heterogeneous types of data sources such as papers, patents, reports, Web news, Web magazines, and collective intelligence data. It consists of two main parts of descriptive analytics and prescriptive analytics. Once given a researcher, the descriptive analytics part provides results from activity history and research power w.r.t the designated researcher. Then, prescriptive analytics part suggests a group of role model researchers to the researcher, as well as how to be like the role model researchers. The prescription for the researcher is provided according to 5W1H questions and their corresponding answers. All of the analytical results and their explanations about the given researcher are automatically generated and saved to a report. This researcher-centric prescriptive analytics has not been introduced before and it is useful tool to understand the designated researcher in the perspective of prescriptive as well as descriptive analytics.

Information Retrieval Techniques to Grasp User Intention in Pervasive Computing Environment

This paper contains a method to construct context data which can help an application grasp user intention in pervasive computing environment (PCE). There are various devices in which a user is interested for the user intention (intended behavior such as entering, reading and sleeping). And the core of PCE is to provide appropriate services adapted for grasped user intention through processing context information received from device sensors. Therefore, this paper suggests an approach based on co-occurrence and statistical method, kinds of information retrieval technique, to grasp user intention based on diverse device sensors (context information), including both physical and logical objects.

Research Advising System Based on Prescriptive Analytics

As the amount of data increases enormously, business analytics such as descriptive, predictive, and prescriptive analytics is one of the most important topics for better decision making especially for CTO or CIO in corporate. Prescriptive analytics shows fundamental difference with descriptive analytics and predictive analytics in that it requires high-value alternative actions or decisions to achieve a given goal. However, only a few studies have been introduced since it is a emerging technology. Thus, this study aims to trigger research on this technical area by implementing a prescriptive analytics system and by verifying it in the point of usability and usefulness. The system, InSciTe Advisory, is focused on improving research performance and is based on 5W1H questions to build actionable strategies to achieve a given goal. The comparison evaluation of the system with Elsevier SciVal showed a rate of 118.8% in usefulness and reliability.

Solving English Questions through Applying Collective Intelligence

Many researchers have been using n-gram statistics which is providing statistical information about cohesion among words to extract semantic information in web documents. Also, the n-gram has been applied in spell checking system, prediction of user interest and so on. This paper is a fundamental research to estimate lexical cohesion in documents using trigram, 4gram and 5gram offered by Google. The main purpose of this paper is estimating possibilities of Google n-gram using TOEIC question data sets.

Generating Knowledge Map for Acronym-Expansion Recognition

In this paper, we present a method for instance mapping and URI resolving to merge two heterogeneous resources and construct a new semantic network in a viewpoint of Acronym-Expansion. Acronym-Expansion information extracted from two unstructured large dataset can be remapped by using linkage information between instances and measuring string similarity. All the semantic resources and systems are utilized for constructing infrastructures of KISTI’s TOD, a new information analytics project based on semantic technologies.

Application for Temporal Analysis of Scientific Technology Information

In recent, business intelligence becomes one of important issues due to various analyses on technology trends. Especially, understanding the relations and influences between technologies is core property for the high-performed analysis. To do this, a few works have utilized ontologies constructed automatically but still have many errors and it causes difficulty while interpreting technology trends. Therefore this paper introduces an application which visualizes relationships and influences between technologies according to time series. Our application provides clues for intuitive observations of relationship change between technologies.

Domain Terminology Collection for Semantic Interpretation of Sensor Network Data

Many studies have investigated the management of data delivered over sensor networks and attempted to standardize their relations. Sensor data come from numerous tangible and intangible sources, and existing work has focused on the integration and management of the sensor data itself. The data should be interpreted according to the sensor environment and related objects, even though the data type, and even the value, is exactly the same. This means that the sensor data should have semantic connections with all objects, and so a knowledge base that covers all domains should be constructed. In this paper, we suggest a method of domain terminology collection based on Wikipedia category information in order to prepare seed data for such knowledge bases. However, Wikipedia has two weaknesses, namely, loops and unreasonable generalizations in the category structure. To overcome these weaknesses, we utilize a horizontal bootstrapping method for category searches and domain-term collection. Both the category-article and article-link relations defined in Wikipedia are employed as terminology indicators, and we use a new measure to calculate the similarity between categories. By evaluating various aspects of the proposed approach, we show that it outperforms the baseline method, having wider coverage and higher precision. The collected domain terminologies can assist the construction of domain knowledge bases for the semantic interpretation of sensor data.

Similarity Measurement between Objects and Activities for User Intention Modeling

User intention modeling is a core part to provide appropriate services in ubiquitous and pervasive computing. And the modeling should be concentrated on preparing user activities according to objects which user approaches or touches. In other works, they just contribute to constructing the modeling under restricted conditions such as places. In order to prepare wide ranging and important factors, this work proposes similarity measurement between objects and activities. Through an evaluation, we show how effective this work is and provide its contributions.