clarin-pl/combo-seg-models

Segmenter comparison — LAMBO vs COMBO vs Stanza vs Trankit

87 treebanks · segmentation F1 (Tokens / Sents / Words) · LAMBO / COMBO / Stanza / Trankit[large] / Trankit[base] · highest lowest

Treebank	System	Tokens	Sents	Words
Afrikaans AFRIBOOMS	LAMBO	99.87	99.29	99.87
	COMBO	99.80	100.00	99.78
	Stanza	99.99	99.65	99.99
	Trankit[large]	99.84	100.00	99.84
	Trankit[base]	99.72	100.00	99.72
Ancient Hebrew PTNK	LAMBO	99.50	94.60	88.82
	COMBO	100.00	95.43	97.86
	Stanza	100.00	98.18	93.60
Arabic PADT	LAMBO	99.78	73.33	97.39
	COMBO	99.98	76.72	97.52
	Stanza	99.98	83.56	98.03
	Trankit[large]	99.95	96.79	99.39
	Trankit[base]	99.93	96.59	99.22
Armenian ARMTDP	LAMBO	97.64	88.89	96.94
	COMBO	99.62	90.05	98.19
	Stanza	99.92	99.46	99.48
	Trankit[large]	98.52	99.46	97.26
	Trankit[base]	98.41	98.92	97.23
Basque BDT	LAMBO	99.86	99.92	99.86
	COMBO	99.95	99.92	99.92
	Stanza	99.98	100.00	99.98
	Trankit[large]	99.89	100.00	99.89
	Trankit[base]	99.81	99.92	99.81
Bulgarian BTB	LAMBO	99.80	96.02	99.80
	COMBO	99.89	99.01	99.92
	Stanza	99.96	96.50	99.96
	Trankit[large]	99.78	98.79	99.78
	Trankit[base]	99.84	98.25	99.84
Catalan ANCORA	LAMBO	99.80	99.76	99.78
	COMBO	99.98	99.81	99.72
	Stanza	99.97	99.57	99.95
	Trankit[large]	99.94	99.76	99.94
	Trankit[base]	99.94	100.00	99.93
Chinese Chinese GSD	LAMBO	80.00	97.49	80.00
	COMBO	98.32	99.40	98.33
	Stanza	92.79	99.10	92.79
	Trankit[large]	97.75	99.40	97.75
	Trankit[base]	97.01	99.70	97.01
Croatian SET	LAMBO	99.80	95.78	99.80
	COMBO	99.96	99.34	99.95
	Stanza	99.96	97.08	99.96
	Trankit[large]	99.93	99.08	99.93
	Trankit[base]	99.92	99.16	99.92
Czech CAC	LAMBO	99.78	98.10	99.72
	COMBO	99.99	100.00	99.88
	Stanza	99.82	100.00	99.57
	Trankit[large]	99.99	100.00	99.98
	Trankit[base]	99.96	100.00	99.95
Czech CLTT	COMBO	99.10	95.34	98.35
	Stanza	99.23	98.23	99.23
	Trankit[large]	99.89	98.89	99.85
	Trankit[base]	99.82	100.00	99.76
Czech FICTREE	LAMBO	99.68	94.11	99.59
	COMBO	99.97	99.88	99.89
	Stanza	99.98	99.07	99.97
	Trankit[large]	99.98	99.50	99.98
	Trankit[base]	99.97	99.38	99.97
Danish DDT	LAMBO	99.64	93.50	99.64
	COMBO	99.90	97.52	99.92
	Stanza	99.97	91.81	99.97
	Trankit[large]	99.81	95.46	99.81
	Trankit[base]	99.79	95.19	99.79
Dutch ALPINO	LAMBO	99.67	90.86	99.67
	COMBO	99.92	92.22	99.92
	Stanza	99.87	90.08	99.87
	Trankit[large]	99.43	90.65	99.43
	Trankit[base]	99.22	89.88	99.22
Dutch LASSYSMALL	LAMBO	99.73	76.73	99.73
	COMBO	99.97	93.77	99.97
	Stanza	99.87	78.61	99.87
	Trankit[large]	99.36	92.60	99.36
	Trankit[base]	99.21	91.09	99.21
English EWT	LAMBO	98.86	83.79	98.57
	COMBO	99.72	84.23	99.69
	Stanza	99.17	89.16	98.92
	Trankit[large]	98.67	90.49	98.67
	Trankit[base]	98.48	88.35	98.48
Estonian EDT	LAMBO	99.78	92.32	99.78
	COMBO	99.89	96.62	99.97
	Stanza	99.97	92.88	99.97
	Trankit[large]	99.75	96.58	99.75
	Trankit[base]	99.72	96.55	99.72
Estonian EWT	LAMBO	98.71	75.20	98.71
	COMBO	99.23	89.48	99.16
	Stanza	98.79	79.57	98.79
	Trankit[large]	97.76	82.58	97.76
	Trankit[base]	96.96	83.72	96.96
Faroese FARPAHC	COMBO	99.66	94.44	99.52
	Stanza	99.65	93.94	99.64
Finnish FTB	LAMBO	99.89	89.95	99.66
	COMBO	100.00	95.81	99.97
	Stanza	100.00	90.13	99.98
	Trankit[large]	99.84	97.36	99.83
	Trankit[base]	99.75	95.83	99.74
Finnish TDT	LAMBO	99.54	91.69	99.35
	COMBO	99.72	97.62	99.65
	Stanza	99.73	90.70	99.70
	Trankit[large]	99.71	97.22	99.72
	Trankit[base]	99.62	95.98	99.62
French GSD	LAMBO	99.35	96.52	99.01
	COMBO	99.85	96.74	99.82
	Stanza	99.71	95.03	99.50
	Trankit[large]	99.77	98.80	99.72
	Trankit[base]	99.70	96.63	99.66
Galician CTG	LAMBO	99.65	96.30	99.03
	COMBO	99.75	98.61	97.32
	Stanza	99.91	99.30	99.37
	Trankit[large]	99.76	98.44	99.31
	Trankit[base]	99.76	98.09	99.38
German GSD	LAMBO	99.48	83.63	99.47
	COMBO	99.82	92.52	99.78
	Stanza	99.62	83.84	99.60
	Trankit[large]	99.71	89.72	99.72
	Trankit[base]	99.75	92.72	99.75
German HDT	LAMBO	99.86	98.10	99.86
	COMBO	100.00	99.56	100.00
	Stanza	100.00	97.36	100.00
	Trankit[large]	99.92	99.67	99.92
	Trankit[base]	99.90	99.50	99.90
Greek GDT	LAMBO	99.90	90.22	99.85
	COMBO	99.89	94.93	99.68
	Stanza	99.90	93.66	99.90
	Trankit[large]	99.85	93.50	99.85
	Trankit[base]	99.75	93.57	99.75
Hebrew HTB	COMBO	100.00	100.00	93.25
	Stanza	99.98	100.00	92.29
	Trankit[large]	99.81	99.69	96.31
	Trankit[base]	99.79	100.00	96.03
Hebrew IAHLTWIKI	COMBO	98.53	86.54	91.84
	Stanza	99.64	96.78	94.61
Hindi HDTB	LAMBO	99.83	99.20	99.83
	COMBO	99.99	99.20	98.45
	Stanza	100.00	99.52	100.00
	Trankit[large]	99.88	99.91	99.88
	Trankit[base]	99.89	99.64	99.89
Icelandic GC	LAMBO	99.63	94.69	99.63
	COMBO	99.66	97.59	99.73
	Stanza	99.70	95.80	99.70
Icelandic ICEPAHC	LAMBO	99.77	94.33	99.71
	COMBO	99.93	95.01	99.87
	Stanza	99.90	93.07	99.84
Icelandic MODERN	LAMBO	99.45	95.67	99.45
	COMBO	99.23	96.22	99.06
	Stanza	99.24	94.40	99.24
Indonesian GSD	LAMBO	99.71	92.74	99.47
	COMBO	99.80	93.20	99.66
	Stanza	99.88	93.04	99.64
	Trankit[large]	99.89	95.54	99.89
	Trankit[base]	99.86	95.37	99.86
Irish IDT	LAMBO	99.68	97.92	99.68
	COMBO	99.75	97.24	99.81
	Stanza	99.75	97.24	99.75
	Trankit[large]	99.47	98.24	99.47
	Trankit[base]	99.32	97.25	99.32
Italian ISDT	LAMBO	99.77	99.07	99.64
	COMBO	99.95	99.07	99.13
	Stanza	99.93	99.07	99.79
	Trankit[large]	99.88	99.07	99.86
	Trankit[base]	99.88	98.76	99.87
Italian MARKIT	LAMBO	99.92	98.67	99.46
	COMBO	99.98	99.12	98.26
	Stanza	100.00	99.12	99.67
Italian OLD	LAMBO	99.76	95.50	98.20
	COMBO	99.97	99.55	98.61
Italian PARTUT	LAMBO	99.73	100.00	99.67
	COMBO	99.72	99.02	98.64
	Stanza	99.81	100.00	99.82
	Trankit[large]	99.81	100.00	99.79
	Trankit[base]	99.82	100.00	99.81
Italian TWITTIRO	LAMBO	98.73	62.73	98.18
	COMBO	99.22	64.63	98.51
	Stanza	99.18	57.78	98.91
	Trankit[large]	99.15	65.72	98.89
	Trankit[base]	99.22	56.00	99.01
Italian VIT	LAMBO	99.83	96.47	99.61
	COMBO	99.98	96.04	99.24
	Stanza	99.94	95.93	99.61
	Trankit[large]	99.97	98.18	99.84
	Trankit[base]	99.99	96.52	99.81
Japanese GSD	LAMBO	95.78	94.95	95.78
	COMBO	98.21	96.27	98.29
	Stanza	97.37	99.72	97.37
	Trankit[large]	95.25	95.88	95.25
	Trankit[base]	94.57	95.49	94.57
Korean GSD	LAMBO	99.59	94.09	99.59
	COMBO	99.86	98.28	99.88
	Stanza	99.90	96.29	99.90
	Trankit[large]	98.57	98.08	98.57
	Trankit[base]	98.63	97.67	98.63
Korean KAIST	LAMBO	99.91	99.93	99.91
	COMBO	99.96	99.93	99.97
	Stanza	100.00	99.93	100.00
	Trankit[large]	98.70	99.87	98.70
	Trankit[base]	98.79	99.14	98.79
Korean KSL	LAMBO	99.55	99.08	99.55
	COMBO	99.91	99.54	99.83
Latin ITTB	LAMBO	99.86	94.27	99.85
	COMBO	99.99	95.32	99.99
	Stanza	99.99	80.66	99.99
	Trankit[large]	100.00	94.54	100.00
	Trankit[base]	100.00	94.57	100.00
Latin LLCT	LAMBO	99.94	99.49	99.93
	COMBO	100.00	99.49	99.99
	Stanza	99.99	99.32	99.99
Latin UDANTE	COMBO	99.57	99.17	99.27
	Stanza	99.66	98.22	99.30
Latvian LVTB	LAMBO	99.55	97.76	99.55
	COMBO	99.86	97.83	99.86
	Stanza	99.81	98.15	99.81
	Trankit[large]	99.73	98.69	99.73
	Trankit[base]	99.71	99.10	99.71
Lithuanian ALKSNIS	LAMBO	99.93	91.51	99.93
	COMBO	99.60	96.07	99.63
	Stanza	99.94	89.93	99.94
	Trankit[large]	99.84	95.72	99.84
	Trankit[base]	99.82	95.10	99.82
Maltese MUDT	COMBO	99.65	84.35	99.71
	Stanza	99.85	85.35	99.85
Marathi UFAL	COMBO	99.60	84.78	82.91
	Stanza	97.99	89.36	92.89
	Trankit[large]	99.20	69.31	97.22
	Trankit[base]	99.20	60.87	95.25
Naija NSC	LAMBO	99.86	100.00	99.86
	COMBO	100.00	100.00	100.00
	Stanza	99.99	100.00	99.99
Norwegian BOKMAAL	LAMBO	99.63	96.11	99.63
	COMBO	99.89	99.04	99.90
	Stanza	99.88	97.70	99.88
	Trankit[large]	99.88	98.89	99.88
	Trankit[base]	99.88	99.20	99.88
Norwegian NYNORSK	LAMBO	99.73	94.81	99.73
	COMBO	99.96	97.74	99.96
	Stanza	99.97	95.48	99.97
	Trankit[large]	99.84	98.97	99.84
	Trankit[base]	99.81	98.71	99.81
Old East Slavic RNC	LAMBO	97.98	73.48	97.98
	COMBO	99.69	93.88	99.70
	Stanza	99.14	89.29	99.14
Old East Slavic RUTHENIAN	LAMBO	99.72	96.37	99.72
	COMBO	99.91	96.35	99.91
Persian PERDT	LAMBO	99.77	99.83	99.51
	COMBO	99.85	99.82	99.25
	Stanza	99.96	99.73	99.46
Polish PDB	LAMBO	99.42	98.26	99.36
	COMBO	99.94	98.91	99.91
	Stanza	99.85	98.19	99.83
	Trankit[large]	99.93	98.71	99.92
	Trankit[base]	99.91	98.53	99.89
Pomak PHILOTIS	LAMBO	99.81	95.39	99.81
	COMBO	99.81	92.10	99.45
	Stanza	100.00	95.05	100.00
Portuguese BOSQUE	LAMBO	99.64	92.76	99.47
	COMBO	99.84	97.30	98.36
	Stanza	99.85	93.10	99.76
	Trankit[large]	99.75	97.18	99.67
	Trankit[base]	99.70	97.48	99.65
Portuguese DANTESTOCKS	COMBO	99.65	79.03	99.03
Portuguese PETROGOLD	LAMBO	99.51	93.05	99.42
	COMBO	99.72	96.76	98.44
	Stanza	99.71	95.83	99.66
Portuguese PORTTINARI	LAMBO	98.70	88.41	98.63
	COMBO	99.93	99.91	98.99
Romanian NONSTANDARD	LAMBO	98.66	98.86	98.66
	COMBO	98.77	98.00	98.70
	Stanza	98.96	97.53	98.96
	Trankit[large]	98.74	98.00	98.74
	Trankit[base]	98.68	98.57	98.68
Romanian RRT	LAMBO	99.64	96.79	99.64
	COMBO	99.75	97.46	99.74
	Stanza	99.73	95.72	99.73
	Trankit[large]	99.60	98.49	99.60
	Trankit[base]	99.72	97.67	99.72
Romanian SIMONERO	LAMBO	99.42	100.00	99.42
	COMBO	99.63	100.00	99.57
	Stanza	99.77	100.00	99.77
Russian GSD	LAMBO	99.41	97.83	99.41
	COMBO	99.69	99.25	99.75
	Stanza	99.58	97.33	99.58
	Trankit[large]	99.79	99.25	99.79
	Trankit[base]	99.63	98.25	99.63
Russian POETRY	LAMBO	99.36	83.88	99.36
	COMBO	99.79	89.06	99.66
Russian TAIGA	LAMBO	98.57	84.19	98.57
	COMBO	99.20	80.19	99.21
	Stanza	99.21	89.67	99.21
	Trankit[large]	98.90	92.32	98.90
	Trankit[base]	98.77	92.60	98.77
Serbian SET	LAMBO	99.86	94.16	99.86
	COMBO	100.00	97.78	100.00
	Stanza	99.99	98.46	99.99
	Trankit[large]	99.91	100.00	99.91
	Trankit[base]	99.91	99.71	99.91
Slovak SNK	LAMBO	99.77	87.05	99.73
	COMBO	99.59	95.52	99.60
	Stanza	99.96	84.31	99.96
	Trankit[large]	99.94	98.49	99.94
	Trankit[base]	99.93	98.07	99.93
Slovenian SSJ	LAMBO	99.77	97.46	99.77
	COMBO	99.94	97.48	99.95
	Stanza	99.93	99.26	99.93
	Trankit[large]	99.97	100.00	99.97
	Trankit[base]	99.93	99.81	99.93
Spanish ANCORA	LAMBO	99.85	97.97	99.83
	COMBO	99.99	99.19	99.93
	Stanza	99.97	98.49	99.96
	Trankit[large]	99.91	99.39	99.91
	Trankit[base]	99.94	99.13	99.93
Spanish GSD	LAMBO	99.75	95.98	99.61
	COMBO	99.62	98.71	98.93
	Stanza	99.94	95.60	99.80
	Trankit[large]	99.93	99.30	99.88
	Trankit[base]	99.91	98.94	99.88
Swedish LINES	LAMBO	99.68	90.10	99.68
	COMBO	99.95	91.01	99.94
	Stanza	99.94	87.91	99.94
	Trankit[large]	99.89	90.64	99.89
	Trankit[base]	99.73	90.57	99.73
Swedish TALBANKEN	LAMBO	99.81	97.34	99.81
	COMBO	99.62	99.34	99.62
	Stanza	99.97	97.49	99.97
	Trankit[large]	99.91	99.26	99.91
	Trankit[base]	99.87	99.38	99.87
Tamil TTB	COMBO	98.79	100.00	80.69
	Stanza	99.27	98.74	89.61
	Trankit[large]	98.33	100.00	94.44
	Trankit[base]	98.02	100.00	93.64
Telugu MTG	LAMBO	99.79	96.60	99.79
	COMBO	99.79	97.58	99.79
	Stanza	99.79	98.62	99.79
	Trankit[large]	98.89	98.62	98.89
	Trankit[base]	98.89	98.62	98.89
Turkish ATIS	LAMBO	99.88	87.32	99.88
	COMBO	100.00	89.83	100.00
	Stanza	100.00	86.93	100.00
Turkish BOUN	LAMBO	99.47	90.16	96.27
	COMBO	99.56	91.60	96.55
	Stanza	99.58	90.08	96.32
Turkish IMST	LAMBO	99.64	97.39	97.07
	COMBO	99.81	97.50	98.57
	Stanza	99.86	98.16	97.75
	Trankit[large]	99.84	98.32	98.91
	Trankit[base]	99.86	98.18	98.68
Turkish TOURISM	LAMBO	99.87	100.00	99.87
	COMBO	100.00	100.00	100.00
	Stanza	100.00	100.00	100.00
Ukrainian IU	LAMBO	99.54	95.38	99.52
	COMBO	99.86	97.43	99.78
	Stanza	99.79	97.21	99.76
	Trankit[large]	99.77	97.55	99.76
	Trankit[base]	99.78	97.72	99.76
Ukrainian PARLAMINT	LAMBO	99.15	95.97	99.15
	COMBO	99.95	95.98	99.95
Urdu UDTB	LAMBO	99.83	98.60	99.83
	COMBO	99.99	98.60	99.99
	Stanza	100.00	98.88	100.00
	Trankit[large]	99.75	97.67	99.75
	Trankit[base]	99.66	98.32	99.66
Uyghur UDT	LAMBO	99.57	88.12	99.57
	COMBO	99.45	88.19	99.30
	Stanza	99.42	84.69	99.42
	Trankit[large]	97.95	88.95	97.95
	Trankit[base]	97.63	88.51	97.63
Western Armenian ARMTDP	LAMBO	99.79	95.67	99.67
	COMBO	99.81	96.80	98.44
	Stanza	99.95	99.56	99.91