User:Firespeaker/GSoC2014/Progress

trimmed coverage

week		0a	0b	0c	3
date		2014-03-21	2014-04-06	2014-04-21	2014-06-07
revision		r51024	r51765	r52183	r53965
kaz(-kir)
kir(-kaz)
tur(-kir)	SETimes	76.47	79.06	80.08	80.08
kir(-tur)
tur(-uzb)
uzb(-tur)

monodix stems

week	0a	0b	0c	3	4
date	2014-03-21	2014-04-06	2014-04-21	2014-06-07	2014-06-15
revision	r51024	r51765	r52183	r53965	r54459
kaz	11332	11336	11337	11337	11633
kir	13637	13703	13705	13715	13737
tur	11128	11186	11172	11172	11416
uzb	3922	3957	3957	3957	3957

bidix stems

week	0a	0b	0c	3
date	2014-03-21	2014-04-06	2014-04-21	2014-06-07
revision	r51024	r51765	r52183	r53965
kaz-kir	7557	7557	7557	7557
tur-kir	7163	7249	7107	7107
tur-uzb	2416	2416	2416	2416

CG per-token ambiguity

tokens( analyser | CG ) / tokens( analyser )

week		0a	0b	0c	3
date		2014-03-21	2014-04-06	2014-04-21	2014-06-07
revision		r51024	r51765	r52183	r53965
kaz
kir
tur	SETimes	1.76 → 1.5	2.01 → 1.28	2.12 → 1.23	2.12 → 1.24
uzb

lrx per-token ambiguity

tokens( analyser | CG | biltrans | lrx ) / tokens( analyser | CG | biltrans )

week		0a	0b	0c	3
date		2014-03-21	2014-04-06	2014-04-21	2014-06-07
revision		r51024	r51765	r52183	r53965
kaz(-kir)
kir(-kaz)
tur(-kir)	SETimes	1.13155 → 1.01861	1.1099 → 1.02028	1.1102 → 1.02172	1.11029 → 1.02176
kir(-tur)
tur(-uzb)
uzb(-tur)

corpus testvoc

week		0a	0b	0c	3
date		2014-03-21	2014-04-06	2014-04-21	2014-06-07
revision		r51024	r51765	r52183	r53965
kaz(-kir)
kir(-kaz)
tur(-kir)	SETimes	19.67%	6.72%	11.43%	10.39%
kir(-tur)
tur(-uzb)
uzb(-tur)

WER

texts				week	0a	0b	0c	3
name	language	№ words	direction	date	2014-03-21	2014-04-06	2014-04-21	2014-06-07
				revision	r51024	r51765	r52183	r53965
foo	kaz	~200	kaz-kir	dev set 1
foo	kir	~200	kir-kaz
			kir-tur
küçükkuş	tur	339	tur-kir		99.46% ~ 98.66%	58.06% ~ 49.19%	66.67% ~ 54.85%	63.44% ~ 51.88%
			tur-uzb
foo	uzb	~200	uzb-tur
bar	kaz	~200	kaz-kir	dev set 2
bar	kir	~200	kir-kaz
			kir-tur
bar	tur	~200	tur-kir
			tur-uzb
bar	uzb	~200	uzb-tur
baz	kaz	~500	kaz-kir	dev set 3
baz	kir	~500	kir-kaz
			kir-tur
baz	tur	~500	tur-kir
			tur-uzb
baz	uzb	~500	uzb-tur
foo	kaz	~200	kaz-kir	eval set 1
foo	kir	~200	kir-kaz
			kir-tur
foo	tur	~200	tur-kir
			tur-uzb
foo	uzb	~200	uzb-tur
bar	kaz	~200	kaz-kir	eval set 2
bar	kir	~200	kir-kaz
			kir-tur
bar	tur	~200	tur-kir
			tur-uzb
bar	uzb	~200	uzb-tur
baz	kaz	~500	kaz-kir	eval set 3
baz	kir	~500	kir-kaz
			kir-tur
baz	tur	~500	tur-kir
			tur-uzb
baz	uzb	~500	uzb-tur