Start an {\tt nl-tool} process, and use it to do parsing. Any old {\tt nl-tool} processes
are first killed. The current config file needs to include either a
{\tt dialogue\_\-rec\_\-params} declaration (for dialogue apps) or a {\tt translation\_\-rec\_\-params}
declaration (for speech translation apps); the declaration must
contain definitions for {\tt 'package'} and {\tt 'grammar'}. The following is a
typical example of a suitable declaration:
\begin{verbatim}
regulus_config(dialogue_rec_params,
[package=calendar_runtime(recogniser),
grammar='.MAIN',
'rec.Pruning=1600', 'rec.DoNBest=TRUE',
'rec.NumNBest=6']).
\end{verbatim}
Notes:
\begin{itemize}
\item After {\tt NUANCE\_\-PARSER} is successfully invoked, {\tt nl-tool} is used for
ALL parsing, including batch processing with commands like {\tt TRANSLATE\_\-CORPUS}
and Prolog calls to {\tt parse\_\-with\_\-current\_\-parser/6}.
\item The Nuance parser only returns logical forms, not parse trees.
\end{itemize}
