Using Windmill Expansion for Document Retrieval

Liang, Shao, Smart, Paul, Russell, Alistair and Shadbolt, Nigel (2009) Using Windmill Expansion for Document Retrieval. The Open Information Systems Journal, 3, 1-8.


[img] PDF - Accepted Manuscript
Download (178Kb)


SEMIOTIKS aims to utilise online information to support the crucial decision–making of those military and civilian agencies involved in the humanitarian removal of landmines in areas of conflict throughout the world. An analysis of the type of information required for such a task has given rise to four main areas of research: information retrieval, document annotation, summarisation and visualisation. The first stage of the research has focused on information retrieval, and a new algorithm, “Windmill Expansion” (WE) has been proposed to do this. The algorithm uses retrieval feedback techniques for automated query expansion in order to improve the effectiveness of information retrieval. WE is based on the extraction of human–generated written phases for automated query expansion. Top and Second Level expansion terms have been generated and their usefulness evaluated. The evaluation has concentrated on measuring the degree of overlap between the retrieved URLs. The less the overlap, the more useful the information provided. The Top Level expansion terms were found to provide 90% of useful URLs, and the Second Level 83% of useful URLs. Although there was a decline of useful URLs from the Top Level to the Second Level, the quantity of relevant information retrieved has increased. The originality of SEMIOTIKS lies in its use of the WE algorithm to help non–domain specific experts automatically explore domain words for relevant and precise information retrieval.

Item Type: Article
ISSNs: 1874-1339
Related URLs:
Keywords: information retrieval, query expansion, retrieval feedback, humanitarian demining
Divisions : Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Web & Internet Science
Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Agents, Interactions & Complexity
ePrint ID: 267276
Accepted Date and Publication Date:
21 April 2009Published
Date Deposited: 15 Apr 2009 13:38
Last Modified: 31 Mar 2016 14:14
Further Information:Google Scholar

Actions (login required)

View Item View Item

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics