...L.
The only counts appearing in this paper are expectations, so be will not be using special notation to make a distinction between observed and expected values.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...grammar.
A similar, even simpler approach applies to probabilistic finite state (i.e., Hidden Markov) models.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...HREF="node8.html#figcases">1(c)).
We use the notation 25#25 to denote that non-terminal X generates the string 26#26 as a suffix, and 27#27 to denote that X generates 26#26 as a prefix. Thus 28#28 and 29#29 are the probabilities associated with those events.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...corpus.
Corpus and grammar sizes, as well as the recognition performance figures reported here are not up-to-date with respect to the latest version of BeRP. For ACL-94 we expect to have revised results available that reflect the current performance of the system.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...machine.
Unlike the rest of BeRP, this computation is implemented in Lisp/CLOS and could be speeded up considerably if necessary.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...[Jelinek and Mercer1980].
This proportion comes about because in the original system, predating the method described in this paper, bigrams had to be estimated from the SCFG by random sampling. Generating 200,000 sentence samples was found to give good converging estimates for the bigrams. The bigrams from the raw training sentences were then simply added to the randomly generated ones. We later verified that the bigrams estimated from the SCFG were indeed identical to the ones computed directly using the method described here.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
...not.
A further version of this criterion is to check the magnitude of the largest of 64#64's eigenvalues (its spectral radius). If that value is >1, the grammar is inconsistent; if <1, it is consistent.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.

Andreas Stolcke
Fri Jun 28 20:57:43 PDT 1996