\newcommand{\noopsort}[1]{} \newcommand{\printfirst}[2]{#1}
  \newcommand{\singleletter}[1]{#1} \newcommand{\switchargs}[2]{#2#1}
\begin{thebibliography}{1}

\bibitem{Bahl:89}
L.~Bahl, P.~Brown, P.~de~Souza, and R.~Mercer.
\newblock A tree-based statistical language model for natural language speech
  recognition.
\newblock {\em IEEE Transactions on Acoustics, Speech, and Signal Processing},
  37(7), 1989.

\bibitem{Brown:59a}
D.~Brown.
\newblock A note on approximations to discrete probability distributions.
\newblock {\em Information and Control}, 2:386--392, 1959.

\bibitem{Darroch:72}
J.~Darroch and D.~Ratcliff.
\newblock Generalized iterative scaling for log-linear models.
\newblock {\em Ann. Math. Statistics}, 43:1470--1480, 1972.

\bibitem{Lafferty:95}
S.~Della Pietra, V.~Della Pietra, and J.~Lafferty.
\newblock Inducing features of random fields.
\newblock Technical report, Carnegie Mellon University Computer Science
  Technical Report CMU-CS-95-144, 1995.

\end{thebibliography}