@inproceedings{zhang2008.2,
abstract = {Rank-Biased Precision (RBP) is a retrieval
evaluation metric that assigns an effectiveness
score to a ranking by computing a geometricly
weighted sum of document relevance values, with the
monotonicly decreasing weights in the geometric
distribution determined via a persistence
parameter p. Despite exhibiting various
advantageous traits over well known existing
measures such as Average Precision, RBP has the
drawback of requiring the designer of any experiment
to choose a value for p. Here we present a method
that allows retrieval systems evaluated using RBP
with different p values to be compared. The proposed
approach involves calculating two critical
bounding relevance vectors for the original RBP
score, and using those vectors to calculate the
range of possible RBP scores for any other value of
p. Those bounds may then be sufficient to allow the
outright superiority of one system over the other to
be established. In addition, the process can be
modified to handle any RBP residuals associated with
either of the two systems. We believe the adoption
of the comparison process described in this paper
will greatly aid the uptake of RBP in evaluation
experiments.},
author = {Yuye Zhang and Laurence A.~F.~Park and Alistair Moffat},
booktitle = {The Proceedings of the Thirteenth Australasian Document Computing Symposium},
date-added = {2008-10-24 09:26:45 +1100},
date-modified = {2008-11-21 09:21:06 +1100},
keywords = {laurence},
title = {Parameter Sensitivity in Rank-Biased Precision},
url = {https://github.com/lafpark/publications/blob/main/zhang20082.pdf},
year = {2008},
bdsk-url-1 = {http://www.cs.mu.oz.au/~lapark/zhang-park-moffat-ADCS2008.pdf}
}
@inproceedings{guo2008.3,
abstract = {Web page prefetching has been used efficiently to
reduce the access latency problem of the Internet,
its success mainly relies on the accuracy of Web
page prediction. As powerful sequential learning
models, Conditional Random Fields (CRFs) have been
used successfully to improve the Web page prediction
accuracy when the total number of unique Web pages
is small. However, because the training complexity
of CRFs is quadratic to the number of labels, when
applied to a website with a large number of unique
pages, the training of CRFs may become very slow and
even intractable. In this paper, we decrease the
training time and computational resource
requirements of CRFs training by integrating error
correcting output coding (ECOC) method. Moreover,
since the performance of ECOC-based methods
crucially depends on the ECOC code matrix in use, we
employ a coding method, Search Coding, to design the
code matrix of good quality.},
author = {Yong Zhen Guo and Kotagiri Ramamohanarao and Laurence A. F. Park},
booktitle = {Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence},
date-modified = {2008-12-16 12:57:25 +1100},
doi = {10.1109/WIIAT.2008.148},
keywords = {laurence},
title = {Error Correcting Output Coding-Based Conditional Random Fields for Web Page Prediction},
urlold = {http://www.csse.unimelb.edu.au/~lapark/ecoc-crf.pdf},
year = {2008},
bdsk-url-1 = {http://www.csse.unimelb.edu.au/~lapark/ecoc-crf.pdf},
bdsk-url-2 = {http://dx.doi.org/10.1109/WIIAT.2008.148}
}
@inproceedings{guo2008,
abstract = {Web page prefetching is used to reduce the access
latency of th`e Internet. However, if most
prefetched Web pages are not visited by the users in
their subsequent accesses, the limited network
bandwidth and server resources will not be used
efficiently and even worsen the access delay
problem. Therefore, enhancing the Web page
prediction accuracy is a main problem of Web page
prefetching. Conditional Random Fields (CRFs), which
are popular sequential learning models, have already
been successfully used for many Natural Language
Processing (NLP) tasks such as POS tagging, name
entity recognition (NER) and segmentation. In this
paper, we propose the use of CRFs in the field of
Web page prediction. We treat the accessing sessions
of previous Web users as observation sequences and
label each element of these observation sequences to
get the corresponding label sequences, then based on
these observation and label sequences we use CRFs to
train a prediction model and predict the probable
subsequent Web pages for the current users. Our
experimental results show that CRFs can produce
higher Web page prediction accuracy effectively when
compared with other popular techniques like plain
Markov Chains and Hidden Markov Models (HMMs).},
author = {Yong Zhen Guo and Kotagiri Ramamohanarao and Laurence A.~F.~Park},
booktitle = {Proceedings of the 18th European Conference on Artificial Intelligence},
date-added = {2008-06-26 09:08:21 +1000},
date-modified = {2008-10-24 09:49:43 +1100},
keywords = {laurence},
pages = {251-255},
title = {Web Page Prediction Based on Conditional Random Fields},
url = {https://github.com/lafpark/publications/blob/main/guo2008.pdf},
year = {2008},
bdsk-url-1 = {http://www.csse.unimelb.edu.au/~lapark/crf-prediction.pdf}
}
@inproceedings{park2008,
abstract = {Language modelling is new form of information
retrieval that is rapidly becoming the preferred
choice over probabilistic and vector space models,
due to the intuitiveness of the model formulation
and its effectiveness. The language model assumes
that all terms are independent, therefore the
majority of the documents returned to the user will
be those that contain the query terms. By making
this assumption, related documents that do not
contain the query terms will never be found, unless
the related terms are introduced into the query
using a query expansion technique. Unfortunately,
recent attempts at performing a query expansion
using a language model have not been in-line with
the language model, being complex and not intuitive
to the user. In this article, we introduce a simple
method of query expansion using the naive Bayes
assumption, that is in-line with the language model
since it is derived from the language model. We show
how to derive the query expansion term relationships
using probabilistic latent semantic analysis (PLSA).
Through experimentation, we show that using PLSA
query expansion within the language model framework,
we can provide a significant increase in precision.},
author = {Laurence A.~F.~Park and Kotagiri Ramamohanarao},
booktitle = {The Twelfth Pacific-Asia Conference on Knowledge Discovery and Data Mining},
date-added = {2008-02-04 15:51:26 +1100},
date-modified = {2008-06-30 15:34:44 +1000},
doi = {10.1007/978-3-540-68125-0_64},
editor = {Takashi Washio and Einoshin Suzuki and Kai Ming Ting and Akihiro Inokuchi},
keywords = {laurence; language models},
month = {May},
number = {5012},
pages = {681-688},
publisher = {Springer},
series = {LNCS},
title = {Query expansion for the language modelling framework using the naive Bayes assumption},
urlold = {http://www.csse.unimelb.edu.au/~lapark/lm_thesaurus.pdf},
year = {2008},
bdsk-url-1 = {http://www.csse.unimelb.edu.au/~lapark/lm_thesaurus.pdf},
bdsk-url-2 = {http://dx.doi.org/10.1007/978-3-540-68125-0_64}
}
@inproceedings{park2006,
abstract = {A latent semantic thesaurus allows us to use the
term relationships generated by probabilistic latent
semantic analysis (PLSA) in the form of a query
expansion. It has many benefits over a latent
semantic index; one of them being that the weights
used to calculate the thesaurus term relationships
can be different to the weights used during document
retrieval. This article contains an investigation
of the effect of term weighting on the probabilistic
latent semantic term relationships. The effect of
the term weighting is examined through the precision
obtained from queries using the PLSA term
relationships. Through experimentation, we found
that all but one of the document sets used produced
more effective term relationships when using
weighted document-term frequencies, bringing us to
the conclusion that it is more likely that term
relationships will be more effective when using
weighted terms with PLSA. A comparison to the BM25
pseudo-relevance feedback retrieval system showed
that the PLSA weighted thesaurus method was able to
produce an average 9\% increase in average
reciprocal rank. },
author = {Laurence A.~F.~Park and Kotagiri Ramaohanarao},
booktitle = {The 5th String Processing and Information Retrieval Symposium},
date-modified = {2008-12-16 12:48:02 +1100},
doi = {10.1007/978-3-540-89097-3_8},
editor = {Amihood Amir and Andrew Turpin and Alistair Moffat},
keywords = {probabilistic latent semantic analysis; laurence},
pages = {63-74},
title = {The effect of weighted term frequencies on probabilistic latent semantic term relationships},
volume = {5280/2009},
year = {2008},
url = {https://github.com/lafpark/publications/blob/main/weighted-plsa-2008.pdf},
bdsk-url-1 = {http://dx.doi.org/10.1007/978-3-540-89097-3_8}
}
This file was generated by bibtex2html 1.99.