This paper deals with the development of parsing techniques for
the analysis of natural
language sentences. We present a paradigm of a multi- path shift-reduce
parser which
combines two differently structured computational subsystems. The first
uses information
concerning native speakers' preferences, and the second
deals with the linguistic knowledge.
To apply preferences on parsing, we propose a method to rank the alternative
partial analyses
on the basis of parse context and frequency of use effects. The method
is mainly based
on psycholinguistic evidence, since we hope eventually to build a parser
working as closely
as possible to the way native speakers analyse natural sentences. We also
discuss in detail
techniques for optimizing the effectiveness of the proposed model. The
system has worked
successfully in parsing sentences in Modern Greek, a language where the
relatively free word
order characteristic results in many ambiguity problems. The proposed parsing
model is
consistent with many directions in the field of preference-based parsing,
and it is proved to
be adequate in building effective and maintainable natural language analysers.
It is believed
that this model can also be used in parsing sentences in languages other
than Greek.