[SRILM-Announce] SRILM 1.5.10 released

Andreas Stolcke stolcke at speech.sri.com
Thu Jan 7 11:39:01 PST 2010


Happy New Year to all!

The latest version of SRILM can now be downloaded from 
http://www-speech.sri.com/projects/srilm/download.html .

Changes are summarized below.

--Andreas


1.5.10	7 Jan 2010
	
	Functionality:

	* New option ngram -float-counts to allow the -counts option to
	process fractional counts.

	* The LM::pplCountsFile() and LM::countsProb() have been templatized
	(as a function of count type), and the TextStats class now uses double
	float counts, all in support of the above change.

	* New option lattice-tool -word-posteriors-for-sentences for computing
	word posteriors based on confusion networks (contributed by Jing Zheng).

	* lattice-tool now performs confusion network decoding and ngram 
	computation AFTER rescoring or expansion with LMs.  Therefore the two
	operations can be combined in a single run where previously two
	invocations were necessary.

	* Added fsm-to-pfsg map_epsilon= option, to translate FSM <eps> symbols
	to another label.

	* New script filter-event-counts to preprocess a count file for use 
	with ngram -counts .

	* lattice-tool continues processing when one of the lattices specified
	with -in-lattice-list cannot be opened.

	* Regression tests have been moved to module subdirectories
	(lm/test, flm/test, lattice/test) and can now be run from the 
	top-level with "make test".  Decompression of data files for platforms
	that don't support compressed file I/O is now automatic.

	Documentation:

	* Added new FAQ items covering handling of OOVs and zeroprob words,
	based on input from Nitin Madnani.

	* Correction to the man page description of the ngram -count-order
	option:  It limits the maximal order of processed ngrams.

	* Corrected and updated ordered list of processing steps in
	lattice-tool man page.

	Bug fixes:

	* Use double precision to record log probs in TextStats object.

	* Workaround for a deficiency in Intel's 7.00 C++ compiler.

	* lattice-tool was not handling PFSG lattices in (1best or N-best) 
	decoding with a LM.

	* lattice-tool will exit with a non-zero status if any of the lattice
	operations fail.

	* Fixed some format string/argument mismatches that could bite on
	64-bit platforms.

	* Updated usage of sort with key specification to conform to latest
	POSIX standard.  The old syntax was no longer working with recent
	GNU sort versions.



More information about the SRILM-Announce mailing list