Dr Nicola Talbot | School of Computing Sciences | University of East Anglia

# abshtml.bst : BibTeX style file

## Introduction

This BibTeX style file is based on unsrt.bst with two additional fields: abstract and file. The first (abstract) should be fairly self-explanatory, the second field (file) places it's value as the argument to the \url command defined in html.sty. The purpose of this BibTeX style file is to convert a list of publications into a web page with links to the specified files.

## Example

Suppose you have a file sample.bib that looks something like:
@string{ESANN = "Proceedings of the European symposium on artifical neural networks"}

@inproceedings{Cawley2002a,
author    = "Cawley, G. C. and Talbot, N. L. C.",
title     = "Efficient formation of a basis in a kernel induced feature space",
booktitle = ESANN # "~(ESANN 2002)",
pages     = "1--6",
month     = apr,
year      = 2002,
abstract  = "Baudat and Anouar (2001) propose a simple greedy algorithm for
estimation of an approximate basis of the subspace spanned by a set of fixed
vectors embedded in a kernel induced feature space.  The resulting set of
basis vectors can then be used to construct sparse kernel expansions for
classification and regression tasks.  In this paper we describe five
algorithmic improvements to the method of Baudat and Anouar, allowing the
construction of an approximate basis with a computational complexity that is
independent of the number of training patterns, depending only on the number
of basis vectors extracted.",
file      = "esann2002a.pdf"
}

@article{Cawley2002b,
author    = "Cawley, G. C. and Talbot, N. L. C.",
title     = "Improved sparse least-squares support vector machines",
journal   = "Neurocomputing",
volume    = 48,
pages     = "1025--1031",
month     = oct,
year      = 2002,
abstract  = "Suykens \emph{et al.} describe a weighted least-squares
formulation of the support vector machine for regression problems and presents
a simple algorithm for sparse approximation of the typically fully dense
kernel expansions obtained using this method.  In this paper, we present an
improved method for achieving sparsity in least-squares support vector
machines, which takes into account the residuals for all training patterns,
rather than only those incorporated in the sparse kernel expansion.  The
superiority of this algorithm is demonstrated on the motorcycle and Boston
housing datasets.",
file      = "neurocomputing.pdf"
}

@inproceedings{Foxall2002,
author    = "Foxall, R. J. and Cawley, G. C. and Talbot, N. L. C. and Dorling, S. R. and Mandic, D. P.",
title     = "Heteroscedastic regularised kernel regression for prediction of episodes of poor air quality",
booktitle = ESANN # "~(ESANN-2002)",
pages     = "19--24",
month     = apr,
year      = 2002,
abstract  = "A regularised kernel regression model is introduced for data characterised by
a heteroscedastic (input dependent variance) Gaussian noise process.  The
proposed model provides more robust estimates of the conditional mean than
standard models and also confidence intervals (error bars) on predictions.
The benefits of the proposed model are demonstrated for the task of non-linear
prediction of episodes of poor air quality in urban environments.",
file      = "esann2002b.pdf"
}


and suppose you have a file sample.tex that looks like:
\documentclass[a4paper]{article}

\usepackage{html}

\begin{document}

\nocite{*}

\bibliographystyle{abshtml}
\bibliography{sample}
\end{document}

Then the HTML page can be created using the LaTeX2HTML translator:
latex2html -split 0 -noinfo -nonavigation sample

It's not perfect, but it saves typing it all directly into HTML.