@inproceedings{park2004,
abstract = { Latent semantic retrieval methods (unlike vector
space methods) take the document and query vectors
and map them into a topic space to cluster related
terms and documents. This produces a more precise
retrieval but also a long query time. We present a
new method of document retrieval which allows us to
process the latent semantic information into a
hybrid latent semantic-vector space query
mapping. This mapping automatically expands the
users query based on the latent semantic information
in the document set. This expanded query is
processed using a fast vector space method. Since we
have the latent semantic data in a mapping, we are
able to store and retrieve vector information in the
same fast manner that the vector space method
offers. Multiple mappings are combined to produce
hybrid latent semantic retrieval which provide
precision results 5\% greater than the vector space
method and fast query times.},
address = {Los Alamitos, California},
author = {Laurence A.~F.~Park and Kotagiri Ramamohanarao},
booktitle = {The Fourth IEEE International Conference on Data Mining},
date-modified = {2007-10-19 12:18:31 +1000},
doi = {10.1109/ICDM.2004.10085},
editor = {Rajeev Rastogi and Katharina Morik and Max Bramer and Xindong Wu},
keywords = {latent semantic analysis, laurence},
month = {November},
organization = {IEEE Computer Society},
pages = {178--185},
title = {Hybrid pre-query term expansion using Latent Semantic Analysis},
topic = {LSA, thesaurus, query map},
url = {http://www.csse.unimelb.edu.au/~lapark/park_hybridlsa2004.pdf},
year = {2004},
bdsk-url-1 = {%22http://www.cs.mu.oz.au/~lapark/park%5C_hybridlsa2004.pdf%22},
bdsk-url-2 = {http://dx.doi.org/10.1109/ICDM.2004.10085},
bdsk-url-3 = {http://www.csse.unimelb.edu.au/~lapark/park_hybridlsa2004.pdf}
}
@incollection{park2004.2,
address = {Sydney, Australia},
author = {Laurence A.~F.~Park and Kotagiri Ramamohanarao},
booktitle = {The Eighth Pacific-Asia Conference on Knowledge Discovery and Data Mining Workshop},
date-modified = {2007-10-19 12:19:33 +1000},
keywords = {latent semantic analysis; laurence},
month = {May},
pages = {1-10},
title = {Preliminary work on Pre-query term expansion using Latent Semantic Analysis},
topic = {LSA, thesaurus, query map},
publisher = {Springer},
year = {2004}
}
@article{park01.2,
abstract = { Current document retrieval methods use a vector
space similarity measure to give scores of relevance
to documents when related to a specific query. The
central problem with these methods is that they
neglect any spatial information within the documents
in question. We present a new method called Fourier
Domain Scoring (FDS) which takes advantage of this
spatial information, via the Fourier transform, to
give a more accurate ordering of relevance to a
document set. We show that FDS gives an improvement
in precision over the vector space similarity
measures for the common case of Web like queries,
and it gives similar results to the vector space
measures for longer queries. },
author = {Laurence A.~F.~Park and Kotagiri Ramamohanarao and Marimuthu Palaniswami},
date-modified = {2007-10-19 12:19:33 +1000},
doi = {10.1109/TKDE.2004.1277815},
journal = {IEEE Transactions on Knowledge and Data Engineering},
keywords = {information retrieval; laurence},
month = {May},
number = {5},
pages = {529-539},
title = {Fourier Domain Scoring : A novel document ranking method},
url = {http://www.csse.unimelb.edu.au/~lapark/fds_compare.pdf},
volume = {16},
year = {2004},
contribution = {70\%},
era2010rank = {A},
sniprank = {5.42},
citations = {32},
bdsk-url-1 = {http://www.csse.unimelb.edu.au/~lapark/fds_compare3.pdf},
bdsk-url-2 = {http://dx.doi.org/10.1109/TKDE.2004.1277815},
bdsk-url-3 = {http://www.csse.unimelb.edu.au/~lapark/fds_compare.pdf}
}
@phdthesis{parkthesis,
abstract = {The information found on the Internet is growing at
such a rapid rate that soon methods of
searching through text using terms frequencies will
not be enough. At the moment, many Web search
engines are showing signs of imprecision because
they are based on these term counting methods which
do not examine the relationships between the
document terms. These methods begin to fail as the
number of indexed documents increases past an
allowable limit. Natural language processing has
been performed in the past and we have found that it
is only useful within its own domain. For example,
if we use a natural language system to extract
documents from a sporting database, we will find
that the same tool will not be very effective for
medical articles. Spatial methods have been
developed to tackle the problem of the ever growing
World Wide Web. Many have failed but a few have
risen to the level of the frequency based methods
mentioned above. Due to the extra document analysis
performed, the spatial methods are slower than the
frequency based methods and require more storage.
This thesis presents a novel method of information
retrieval entitled ``Spectral Information
Retrieval''. This method achieves the speed of the
vector space methods with the benefits of the
proximity methods to provide an overall high quality
information retrieval system. Rather than using the
spatial locality information (used in proximity
searches), a spectral information retrieval method
utilises the query terms' spectral lo- cality
information (found with the aid of either the
Fourier transform, Cosine transform, Gaussian
transform or Wavelet transform). By combining the
query term spectra, we are able to make fast
proximity calculations and also make use of the many
varieties of vec- tor space method weighting
schemes. This method provides superior results to
existing text based information retrieval systems.
It is shown that spectral information retrieval
methods provide high precision results at query
times comparable to the widely used vector space
methods, when using an index of comparable size to a
vector space method index. This was possible using
com- pression techniques such as spectral component
cropping and quantisation, and speed up techniques
such as early termination. When querying with a
small set of terms, we saw that the spectral
document retrieval methods using a certain vector
space method weighting scheme, always improved the
precision of the vector space method by a sig-
nificant margin (at least 10\%). It is also shown
that the spectral information retrieval system can
be further enhanced when working in conjunction with
a relevance feedback system.},
address = {Australia},
author = {Laurence A.~F.~Park},
date-modified = {2007-10-19 12:19:33 +1000},
keywords = {signal processing; information retrieval; laurence},
school = {The University of Melbourne},
title = {Spectral Based Information Retrieval},
url = {http://www.cs.mu.oz.au/~lapark/laparkSpectralPhD.pdf},
year = {2004},
bdsk-url-1 = {http://www.cs.mu.oz.au/~lapark/laparkSpectralPhD.pdf}
}
@inproceedings{kotagiri2004,
author = {Kotagiri Ramamohanarao and Laurence A. F. Park},
booktitle = {Advances in Computer Science - ASIAN 2004},
doi = {10.1007/b103476},
keywords = {laurence},
month = {December},
pages = {407-417},
publisher = {Springer Berlin / Heidelberg},
series = {Lecture Notes in Computer Science},
title = {Spectral-Based Document Retrieval},
volume = {3321},
year = {2004},
bdsk-url-1 = {http://dx.doi.org/10.1007/b103476}
}
This file was generated by bibtex2html 1.99.