Abstract | ||
---|---|---|
Most systems that manage distributed information on Internet have difficulties in retrieving relevant information for they are not able to include the exact semantics of retrieval queries that users request. In this paper, we propose an automatic query expansion method based on term distribution which naturally reflects semantics of retrieval terms in order to enhance the performance of information retrieval. The SVD technique in the LSI is utilized in the proposed method to measure the term distribution which appears similar to a query. Terms appearing most similar to the query in consideration of the distribution are appended to the query. Thereby, the query can hit documents without having common terms but with common concepts. An automatic term reduction technique is also proposed which does not choose to append all the terms in the same distribution area. The experimental results show our method maintains comparable retrieval effectiveness as the other LSI methods without having to append many unnecessary terms. |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/ICPADS.1997.652612 | ICPADS |
Keywords | Field | DocType |
automatic term reduction technique,intelligent information retrieval,information retrieval,distribution area,common term,query expansion,retrieval term,term distribution,retrieval query,lsi method,automatic query expansion method,comparable retrieval effectiveness,information management,weight,computer science,semantics,engineering management,internet,similarity,software engineering | Query optimization,Web search query,Data mining,Query language,Information retrieval,Query expansion,Computer science,Sargable,Web query classification,Ranking (information retrieval),Query by Example | Conference |
ISBN | Citations | PageRank |
0-8186-8227-2 | 1 | 0.36 |
References | Authors | |
3 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jae Hyun Lim | 1 | 29 | 2.91 |
Youngchan Kim | 2 | 31 | 4.82 |
Hyonwoo Seung | 3 | 26 | 4.40 |
Jun Hwang | 4 | 1 | 0.36 |
Heung-Nam Kim | 5 | 563 | 37.59 |