Descriptive statistics (mean and stdev apart from the first two and the last column) for the UD treebanks used in SR’18 (UD v2.0) and SR’19 (UD v2.3). S: number of submissions, count: number of sentences in a test set, MDD: mean dependency distance, MFS: mean flux size, MFW: mean flux weight, MA: mean arity, NP: percentage of non-projective sentences. For the tree-based metrics (MDD, MFS, MFW, MA), macro-average values are reported. For SR’18, we follow the notation for treebanks as used in the shared task (only language code); in parentheses we list treebank names.
. | . | S . | count . | depth . | length . | MDD . | MFS . | MFW . | MA . | NP . |
---|---|---|---|---|---|---|---|---|---|---|
SR’18 | ar (padt) | 3 | 676 | 7.37±3.29 | 38.5±30.38 | 2.61±0.93 | 2.61±0.93 | 1.44±0.26 | 0.94±0.08 | 1.48 |
cs (pdt) | 2 | 9,876 | 3.95±1.99 | 14.49±9.43 | 2.12±0.74 | 2.12±0.74 | 1.19±0.29 | 0.86±0.18 | 9.91 | |
es (ancora) | 6 | 1,719 | 5.21±2.2 | 26.88±15.7 | 2.47±0.66 | 2.47±0.66 | 1.33±0.25 | 0.93±0.09 | 2.39 | |
en (ewt) | 8 | 2,061 | 2.71±1.88 | 10.57±9.55 | 1.86±0.95 | 1.86±0.95 | 1.02±0.42 | 0.75±0.3 | 1.65 | |
fi (tdt) | 3 | 1,525 | 3.48±1.81 | 11.42±7.22 | 2.02±0.62 | 2.02±0.62 | 1.16±0.23 | 0.86±0.12 | 5.57 | |
fr (gsd) | 5 | 416 | 4.33±1.75 | 21.21±12.57 | 2.44±0.59 | 2.44±0.59 | 1.28±0.25 | 0.93±0.07 | 2.16 | |
it (isdt) | 4 | 480 | 4.38±2.23 | 19.14±14.07 | 2.19±0.61 | 2.19±0.61 | 1.23±0.23 | 0.91±0.06 | 2.29 | |
nl (alpino) | 4 | 685 | 3.74±1.86 | 15.03±9.11 | 2.48±1.05 | 2.48±1.05 | 1.21±0.39 | 0.85±0.22 | 20.15 | |
pt (bosque) | 4 | 476 | 4.32±2.12 | 18.58±12.11 | 2.25±0.63 | 2.25±0.63 | 1.23±0.27 | 0.9±0.13 | 4.20 | |
ru (syntagrus) | 2 | 6,366 | 4.1±1.96 | 14.65±9.14 | 2.12±0.66 | 2.12±0.66 | 1.23±0.27 | 0.88±0.13 | 8.37 | |
SR’19 | ar_padt | 4 | 680 | 7.38±3.28 | 38.54±30.34 | 2.6±0.93 | 2.6±0.93 | 1.45±0.26 | 0.94±0.08 | 1.76 |
en_ewt | 5 | 2,077 | 2.72±1.88 | 10.6±9.62 | 1.87±0.95 | 1.87±0.95 | 1.02±0.42 | 0.75±0.3 | 1.54 | |
en_gum | 11 | 778 | 3.69±1.91 | 15.0±10.63 | 2.14±0.75 | 2.14±0.75 | 1.16±0.31 | 0.85±0.2 | 3.08 | |
en_lines | 11 | 914 | 3.55±1.6 | 14.97±9.56 | 2.27±0.62 | 2.27±0.62 | 1.2±0.23 | 0.89±0.11 | 4.60 | |
en_partut | 11 | 153 | 4.52±2.01 | 20.06±9.77 | 2.48±0.51 | 2.48±0.51 | 1.26±0.21 | 0.93±0.05 | 0.65 | |
es_ancora | 6 | 1,721 | 5.2±2.2 | 26.87±15.7 | 2.47±0.66 | 2.47±0.66 | 1.33±0.25 | 0.93±0.09 | 2.38 | |
es_gsd | 6 | 426 | 5.06±2.25 | 25.18±16.43 | 2.41±0.57 | 2.41±0.57 | 1.31±0.23 | 0.94±0.05 | 4.69 | |
fr_gsd | 7 | 416 | 4.41±1.78 | 21.22±12.58 | 2.41±0.58 | 2.41±0.58 | 1.28±0.25 | 0.93±0.07 | 1.20 | |
fr_partut | 7 | 110 | 4.85±1.82 | 21.84±10.01 | 2.44±0.46 | 2.44±0.46 | 1.29±0.21 | 0.94±0.03 | 0.91 | |
fr_sequoia | 7 | 456 | 4.01±2.21 | 19.66±15.61 | 2.13±0.84 | 2.13±0.84 | 1.16±0.37 | 0.84±0.25 | 0.88 | |
hi_hdtb | 5 | 1,684 | 4.19±1.48 | 19.6±8.99 | 2.96±0.82 | 2.96±0.82 | 1.48±0.23 | 0.94±0.03 | 8.91 | |
id_gsd | 5 | 557 | 4.57±1.85 | 18.02±12.39 | 2.04±0.54 | 2.04±0.54 | 1.22±0.2 | 0.92±0.07 | 0.72 | |
ja_gsd | 6 | 551 | 4.36±1.97 | 20.25±13.35 | 2.43±0.66 | 2.43±0.66 | 1.4±0.32 | 0.92±0.09 | 0.00 | |
ko_gsd | 5 | 989 | 3.59±1.78 | 10.29±6.77 | 2.21±0.79 | 2.21±0.79 | 1.33±0.36 | 0.86±0.1 | 9.20 | |
ko_kaist | 4 | 2,287 | 3.86±1.54 | 11.0±4.56 | 2.27±0.67 | 2.27±0.67 | 1.44±0.32 | 0.89±0.07 | 19.15 | |
pt_bosque | 5 | 477 | 4.32±2.11 | 18.57±12.09 | 2.25±0.63 | 2.25±0.63 | 1.23±0.27 | 0.9±0.13 | 4.40 | |
pt_gsd | 5 | 1,204 | 4.85±1.87 | 22.74±12.2 | 2.39±0.55 | 2.39±0.55 | 1.31±0.23 | 0.94±0.05 | 1.66 | |
ru_gsd | 5 | 601 | 4.11±1.69 | 15.83±10.24 | 2.12±0.69 | 2.12±0.69 | 1.24±0.21 | 0.91±0.06 | 4.49 | |
ru_syntagrus | 4 | 6,491 | 4.08±1.94 | 14.78±9.24 | 2.13±0.65 | 2.13±0.65 | 1.23±0.26 | 0.88±0.13 | 6.49 | |
zh_gsd | 7 | 500 | 4.22±1.08 | 20.64±10.17 | 2.98±0.84 | 2.98±0.84 | 1.46±0.27 | 0.94±0.03 | 0.40 |
. | . | S . | count . | depth . | length . | MDD . | MFS . | MFW . | MA . | NP . |
---|---|---|---|---|---|---|---|---|---|---|
SR’18 | ar (padt) | 3 | 676 | 7.37±3.29 | 38.5±30.38 | 2.61±0.93 | 2.61±0.93 | 1.44±0.26 | 0.94±0.08 | 1.48 |
cs (pdt) | 2 | 9,876 | 3.95±1.99 | 14.49±9.43 | 2.12±0.74 | 2.12±0.74 | 1.19±0.29 | 0.86±0.18 | 9.91 | |
es (ancora) | 6 | 1,719 | 5.21±2.2 | 26.88±15.7 | 2.47±0.66 | 2.47±0.66 | 1.33±0.25 | 0.93±0.09 | 2.39 | |
en (ewt) | 8 | 2,061 | 2.71±1.88 | 10.57±9.55 | 1.86±0.95 | 1.86±0.95 | 1.02±0.42 | 0.75±0.3 | 1.65 | |
fi (tdt) | 3 | 1,525 | 3.48±1.81 | 11.42±7.22 | 2.02±0.62 | 2.02±0.62 | 1.16±0.23 | 0.86±0.12 | 5.57 | |
fr (gsd) | 5 | 416 | 4.33±1.75 | 21.21±12.57 | 2.44±0.59 | 2.44±0.59 | 1.28±0.25 | 0.93±0.07 | 2.16 | |
it (isdt) | 4 | 480 | 4.38±2.23 | 19.14±14.07 | 2.19±0.61 | 2.19±0.61 | 1.23±0.23 | 0.91±0.06 | 2.29 | |
nl (alpino) | 4 | 685 | 3.74±1.86 | 15.03±9.11 | 2.48±1.05 | 2.48±1.05 | 1.21±0.39 | 0.85±0.22 | 20.15 | |
pt (bosque) | 4 | 476 | 4.32±2.12 | 18.58±12.11 | 2.25±0.63 | 2.25±0.63 | 1.23±0.27 | 0.9±0.13 | 4.20 | |
ru (syntagrus) | 2 | 6,366 | 4.1±1.96 | 14.65±9.14 | 2.12±0.66 | 2.12±0.66 | 1.23±0.27 | 0.88±0.13 | 8.37 | |
SR’19 | ar_padt | 4 | 680 | 7.38±3.28 | 38.54±30.34 | 2.6±0.93 | 2.6±0.93 | 1.45±0.26 | 0.94±0.08 | 1.76 |
en_ewt | 5 | 2,077 | 2.72±1.88 | 10.6±9.62 | 1.87±0.95 | 1.87±0.95 | 1.02±0.42 | 0.75±0.3 | 1.54 | |
en_gum | 11 | 778 | 3.69±1.91 | 15.0±10.63 | 2.14±0.75 | 2.14±0.75 | 1.16±0.31 | 0.85±0.2 | 3.08 | |
en_lines | 11 | 914 | 3.55±1.6 | 14.97±9.56 | 2.27±0.62 | 2.27±0.62 | 1.2±0.23 | 0.89±0.11 | 4.60 | |
en_partut | 11 | 153 | 4.52±2.01 | 20.06±9.77 | 2.48±0.51 | 2.48±0.51 | 1.26±0.21 | 0.93±0.05 | 0.65 | |
es_ancora | 6 | 1,721 | 5.2±2.2 | 26.87±15.7 | 2.47±0.66 | 2.47±0.66 | 1.33±0.25 | 0.93±0.09 | 2.38 | |
es_gsd | 6 | 426 | 5.06±2.25 | 25.18±16.43 | 2.41±0.57 | 2.41±0.57 | 1.31±0.23 | 0.94±0.05 | 4.69 | |
fr_gsd | 7 | 416 | 4.41±1.78 | 21.22±12.58 | 2.41±0.58 | 2.41±0.58 | 1.28±0.25 | 0.93±0.07 | 1.20 | |
fr_partut | 7 | 110 | 4.85±1.82 | 21.84±10.01 | 2.44±0.46 | 2.44±0.46 | 1.29±0.21 | 0.94±0.03 | 0.91 | |
fr_sequoia | 7 | 456 | 4.01±2.21 | 19.66±15.61 | 2.13±0.84 | 2.13±0.84 | 1.16±0.37 | 0.84±0.25 | 0.88 | |
hi_hdtb | 5 | 1,684 | 4.19±1.48 | 19.6±8.99 | 2.96±0.82 | 2.96±0.82 | 1.48±0.23 | 0.94±0.03 | 8.91 | |
id_gsd | 5 | 557 | 4.57±1.85 | 18.02±12.39 | 2.04±0.54 | 2.04±0.54 | 1.22±0.2 | 0.92±0.07 | 0.72 | |
ja_gsd | 6 | 551 | 4.36±1.97 | 20.25±13.35 | 2.43±0.66 | 2.43±0.66 | 1.4±0.32 | 0.92±0.09 | 0.00 | |
ko_gsd | 5 | 989 | 3.59±1.78 | 10.29±6.77 | 2.21±0.79 | 2.21±0.79 | 1.33±0.36 | 0.86±0.1 | 9.20 | |
ko_kaist | 4 | 2,287 | 3.86±1.54 | 11.0±4.56 | 2.27±0.67 | 2.27±0.67 | 1.44±0.32 | 0.89±0.07 | 19.15 | |
pt_bosque | 5 | 477 | 4.32±2.11 | 18.57±12.09 | 2.25±0.63 | 2.25±0.63 | 1.23±0.27 | 0.9±0.13 | 4.40 | |
pt_gsd | 5 | 1,204 | 4.85±1.87 | 22.74±12.2 | 2.39±0.55 | 2.39±0.55 | 1.31±0.23 | 0.94±0.05 | 1.66 | |
ru_gsd | 5 | 601 | 4.11±1.69 | 15.83±10.24 | 2.12±0.69 | 2.12±0.69 | 1.24±0.21 | 0.91±0.06 | 4.49 | |
ru_syntagrus | 4 | 6,491 | 4.08±1.94 | 14.78±9.24 | 2.13±0.65 | 2.13±0.65 | 1.23±0.26 | 0.88±0.13 | 6.49 | |
zh_gsd | 7 | 500 | 4.22±1.08 | 20.64±10.17 | 2.98±0.84 | 2.98±0.84 | 1.46±0.27 | 0.94±0.03 | 0.40 |