cdec-dtrain - Mirror of https://github.com/pks/cdec-dtrain.git

Age	Commit message (Collapse)	Author
2010-07-24	compile	graehl
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@401 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-23	sparse_vector use google::dense_hash_map, fsa scan logging	graehl
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@383 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-21	Fixing errors.	olivia.buzek
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@361 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-21	Little bug fix to EM clustering	trevor.cohn
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@357 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-20	tests compile	graehl
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@332 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-19	use lexer instead of handwritten parser	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@319 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-19	Added count pruning.	trevor.cohn
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@318 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-19	Fixed a couple of bugs in the monolingual context extractor	trevor.cohn
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@314 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-18	??	trevor.cohn
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@312 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-18	Changed to UTF8	trevor.cohn
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@311 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-15	fix potential namespace conflict:	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@271 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-15	Massacred the pipeline to support source language phrases and contexts.	trevor.cohn
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@255 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-14	Added facility to get source or both language phrases/contexts. Need to fix ↵	trevor.cohn
	the scripts first before using this new feature. git-svn-id: https://ws10smt.googlecode.com/svn/trunk@250 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-13	revert xsing features	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@239 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-13	singleton features	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@237 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-13	major speed up using DFA parser	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@235 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-13	start moving toward striped grammar lexer	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@233 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-13	cdec now supports coarse-to-fine decoding (for SCFG only).	adam.d.lopez
	CTF has several options: -coarse_to_fine_beam_prune=<double> (required to activate CTF) assign an alpha parameter for pruning the coarse foreast -ctf_beam_widen=<double> (optional, defaults to 2.0): ratio to widen coarse pruning beam if fine parse fails. -ctf_num_widenings=<int> (optional, defaults to 2): number of times to widen coarse beam before defaulting to exhaustive source parsing -ctf_no_exhaustive (optional) do not attempt exhaustive parse if CTF fails to find a parse. Additionally, script extools/coarsen_grammar.pl will create a coarse-to-fine grammar (for X?? categories only). cdec will read CTF grammars in a format identical to the original, in which refinements of a rule immediately follow the coarse projection, preceded by an additional whitespace character. Not fully tested, but should be backwards compatible. Also not yet integrated into pipelines, but should work on the command line. git-svn-id: https://ws10smt.googlecode.com/svn/trunk@231 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-09	Fixing backoff grammar.	olivia.buzek
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@214 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-09	Added a bunch of features.	philblunsom
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@209 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-08	Adding backoff grammar and BackoffRule feature.	olivia.buzek
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@191 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-08	Fixed up evaluation pipeline. Should work now ...	philblunsom
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@183 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-07	fix bugs	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@180 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-07	In unfinished state. DO NOT USE	philblunsom
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@179 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-06	more	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@164 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-06	warnings	graehl
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@157 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-06	featurizer	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@154 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-05	use better features	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@135 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-02	filter and score in a single file	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@118 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-02	sort / filter rules by p(e\|f), permit more features	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@100 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-01	filt typo that makes filtering too permissive	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@95 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-01	comment	graehl
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@90 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-07-01	use named features	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@89 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-06-29	bug fix	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@65 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-06-29	isolate warning messages	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@56 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-06-25	optionally use unlimited cache	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@27 ec762483-ff6d-05da-a07a-a48fb63a330f
2010-06-22	initial checkin	redpony
	git-svn-id: https://ws10smt.googlecode.com/svn/trunk@2 ec762483-ff6d-05da-a07a-a48fb63a330f