ELRA Conference on Language Resources and Evaluation '98:
Rapid Language Model Development for New Task Domains
Please download a copy of the paper by clicking here:
ELRA LREC '98 Paper in gzip'ed PostScript format
(~34K).
ELRA LREC '98 Paper in PostScript format (not compressed)
(~97K).
Abstract:
Data sparseness has been regularly indicted as the primary problem in
statistical language modelling. We go one step further to consider the
situation when no text data is available for the target domain. We
present two techniques for building efficient language models quickly
for new domains. The first technique is based on using a context-free
grammar to generate a corpus of word collocations. The second is an
adaptation technique based on using out-of-domain corpora to estimate
target domain language models. We report results of successfully using
these two techniques individually and in combination to build
efficient models for a spontaneous speech recognition task in a
medium-sized vocabulary domain.
Last Change: 98 Jun 10 by
ringger@cs.rochester.edu