Summarizing methods and text mining are key topics in research conducted by the
Software Engineering Lab members.
This year, the focus was on techniques to summarize scientific documents retrieved by general purpose search engines. We were interested in the summarization on the fly. Results of our investigations and tests were presented at the IEEE Japan-China on Frontier of Computer Science and Technology Workshop, the IEEE SIBIRCON-2008 Conference, and.
The aim of our work in the area of text mining was to improve Web search service. The prototype of the system generating summaries on the fly was created. Our study was supported by a grant from the University of Aizu Competitive Research Funding. Students of our lab were involved in this research. Results of the research were presented at the 2008 Remote Engineering and Virtual Instrumentation International Conference and at The 11th International Conference on Humans and Computers (HC 2008).
||D. Vazhenin, S. Satake, S. Ishikawa, and V. Klyuev. A Document
Retrieval Framework for Scientific Publications. In Proc. of the IEEE
SIBIRCON-2008 Conference, pages pp. 95 – 99, Novosibirsk, Russia, 2008.
|In the academic area, the Internet is used as a scientific resource. However, finding
appropriate information on the Web remains difficult. To simplify this process, we
designed the document retrieval framework to retrieve scientific publications from
the Web. In this paper, we present the architecture of the proposed tool and results
of prelimenary test evaluating its quality. This tool can be used by researchers and
students when they search for scientific information on the Internet.
||S. Satake, S. Ishikawa, D. Vazhenin, and V. Klyuev. A Summarizer for
Document Retrieval on the Web. In Proc. of the 2008 Remote Engineering
and Virtual Instrumentation International Conference, page CD edition 5 pp.
University of Applied Sciences, Dusseldorf, Germany, 2008.
|Searching is the most common task performed on the Web. General purpose search
engines are very advanced but finding relevant information is still difficult. Small
snippets generated by search engines are evidence of existence of query keywords in
the retrieved documents. In many cases, they are not indicative, and users cannot
evaluate the relevance of documents. We propose a document retrieval framework to
support searching for scientific publications. A prototype, we have designed, works as
a front-end part of a general purpose search engine. It creates summaries of retrieved
pages on the fly and presents them to the end user. Preliminary tests showed that
this approach is promising.
||S. Ishikawa, D. Vazhenin, S. Satake, and V. Klyuev. A Web Retrieval
and Summarizing Tool. In Proc. of the XXXIX Conference on Control Processes
and Stability, pages pp. 395 – 400, St. Petersburg State University,
|These days, the Internet is used as a scientific resource. However, finding appropriate
information on the Web remains difficult. To simplify this process, we designed the
web retrieval and summarizing tool to retrieve scientific publications from the Web.
In this paper, we present the system architecture of the proposed tool and results of
preliminary experiments evaluating its quality. This tool can be used by researchers
and students when they search for scientific information on the Internet.
||D. Vazhenin, S. Satake, S.Ishikawa, and V. Klyuev. A Semantic Based
Summarizing Tool for a General Purpose Search Engine. In Proc of the 11th
International Conference on Humans and Computers, pages pp. 349 – 356,
|we designed an intelligent summarizing tool for the scientific publications retrieved
from the Web. In this paper, we demonstrate how our framework is convenient to the
||V. Klyuev. An Approach to Implementing an Intelligent Web Search.
In Proc. Of the IEEE Japan-China on Frontier of Computer Science and
Technology, pages pp 125 – 130, Nagasaki,Japan, December 2008.
|The functional approach to present English texts in the memory of computers makes
it possible to keep semantic relations between words. These relations can be taken
into account when indexing documents and when performing searching. Utilizing this
approach, it is possible to use a natural language to express user queries. In many
cases, this way is more usual for users to describe their information needs compared
to the keyword style. The factoid question answering task is one of the possible its
applications. Key components of the prototype of a system utilizing this approach
||V. Klyuev. the University of Aizu Competitive Research Funding, 2008.
||V. Klyuev, Apr. 2008.
Member, IEEE and ACM
||Takaaki Suzuki. Graduation Thesis: A Directory Search Tool with
Images and Summaries, University of Aizu, 2009.
Thesis Advisor: Klyuev, V.
||Yuta Shibasaki. Graduation Thesis: Finding the Right Keywords: A
Tool to Support Users, University of Aizu, 2009.
|TThesis Advisor: Klyuev, V.