SRILM 1.1.1 released
Andreas Stolcke
stolcke at speech.sri.com
Sat Jul 21 11:23:32 PDT 2001
A new version of the SRI LM toolkit is now available for download from
http://www.speech.sri.com/projects/srilm/download.html .
A list of changes is appended below.
If you are a regular user of SRILM please join the "srilm-user" mailing list.
See http://www.speech.sri.com/projects/srilm/welcome.html#srilm-user for
more information.
Enjoy,
--Andreas
Functionality:
* WordMesh: new interface to record reference word string in alignment.
* nbest-lattice: confusion networks can now record reference words
if specified with -reference, and are preserved by -write/-read.
* replace-words-with-classes now has option to process ngram count
files (have_counts=1).
* merge-nbest: new utility to merge N-best hyps from multiple lists.
* wlat-stats: new utility to compute statistics of word posterior
lattices.
Bug fixes:
* GT discounting: fixed anomaly due to different floating point
precision on x86 platforms.
* anti-ngram(1): documented options previously omitted.
* WordMesh: reading/writing of confusion networks now preserves
total posterior mass.
* Changed the hypothesis alignment order in nbest-optimize to be
more compatible with decoding in nbest-lattice: first align nbest
hyps in order of decreasing (initial) scores, then align reference.
nbest-optimize -no-reorder keeps the old behavior (with references
anchoring the alignment). All scores and initial lambdas are now
used to compute initial posterior hyp probabilities to guide the
hypothesis alignment; thus, it now makes sense to restart an
optimization with partially optimized weights to revise the
alignments.
* nbest-optimize now warns about missing or incomplete score files.
* Fixed a memory access error in nbest-optimize -1best.
* Fixed weight normalization in nbest-optimize when first element is 0.
* Miscellaneous fixes for compile under RH Linux 7.0.
More information about the SRILM-User
mailing list