Semantic Search Engine

D. Manjula () and T. V. Geetha ()
Additional contact information
D. Manjula: Department of Computer Science and Engineering, Anna University, Chennai-600 025, India
T. V. Geetha: Department of Computer Science and Engineering, Anna University, Chennai-600 025, India

Journal of Information & Knowledge Management (JIKM), 2004, vol. 03, issue 01, 107-117

Abstract: Currently existing search engines index documents only by words and as a result, when a query can be interpreted in different senses, the irrelevant results are obtained in the midst of relevant results. A semantic search engine is proposed here which indexes documents both by words and senses and as a result tries to avoid the irrelevant results. The "crawler" traverses the worldwide web and the normalized documents are sent to the disambiguator module, which identifies the top few sense(s) of ambiguous words by employing a weighted disambiguation algorithm. The documents are then indexed by the words and the senses. The query is also disambiguated in a similar manner and retrieval is performed by matching both the sense and the word. The performance of the semantic search engine is compared against traditional word based indexing and also against the commercial search engines like Google, Yahoo, Hotbot and Lycos. The results show an impressive precision for the semantic search engine compared to other engines, particularly for ambiguous queries.

Keywords: Search engine; Information retrieval; Word sense disambiguation; Natural language processing; Semantics (search for similar items in EconPapers)
Date: 2004
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219649204000729
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:jikmxx:v:03:y:2004:i:01:n:s0219649204000729

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219649204000729

Access Statistics for this article

Journal of Information & Knowledge Management (JIKM) is currently edited by Professor Suliman Hawamdeh

More articles in Journal of Information & Knowledge Management (JIKM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().