diff --git a/UD_any/results/results_tokeparser_seq_order_15_09_20.txt b/UD_any/results/results_tokeparser_seq_order_15_09_20.txt new file mode 100644 index 0000000000000000000000000000000000000000..bce9d50c11f28047e95b33c376b439056cd3a916 --- /dev/null +++ b/UD_any/results/results_tokeparser_seq_order_15_09_20.txt @@ -0,0 +1,304 @@ +A : tokenizer->tagger->morpho->lemma->parser+seq +B : tokenizer->tagger->lemma->morpho->parser+seq +C : tokenizer->morpho->tagger->lemma->parser+seq +D : tokenizer->morpho->lemma->tagger->parser+seq +E : tokenizer->lemma->morpho->tagger->parser+seq +F : tokenizer->lemma->morpho->tagger->parser+seq + +Corpus Metric F1.score Model +-------------------------------------------------------------------------------- +UD_English-EWT LAS 76.72[±0.24]% tokeparser_seq_F +UD_English-EWT LAS 76.83[±0.34]% tokeparser_seq_E +UD_English-EWT LAS 76.92[±0.20]% tokeparser_seq_C +UD_English-EWT LAS 76.96[±0.24]% tokeparser_seq_D +UD_English-EWT LAS 77.11[±0.52]% tokeparser_seq_A +UD_English-EWT LAS 77.25[±0.08]% tokeparser_seq_B + +UD_English-EWT Lemmas 96.89[±0.06]% tokeparser_seq_E +UD_English-EWT Lemmas 96.89[±0.16]% tokeparser_seq_F +UD_English-EWT Lemmas 96.93[±0.04]% tokeparser_seq_D +UD_English-EWT Lemmas 96.93[±0.05]% tokeparser_seq_C +UD_English-EWT Lemmas 97.03[±0.03]% tokeparser_seq_A +UD_English-EWT Lemmas 97.07[±0.04]% tokeparser_seq_B + +UD_English-EWT Sentences 68.56[±0.76]% tokeparser_seq_D +UD_English-EWT Sentences 68.75[±0.83]% tokeparser_seq_E +UD_English-EWT Sentences 68.84[±0.52]% tokeparser_seq_F +UD_English-EWT Sentences 69.27[±0.80]% tokeparser_seq_C +UD_English-EWT Sentences 69.37[±0.30]% tokeparser_seq_A +UD_English-EWT Sentences 69.38[±0.35]% tokeparser_seq_B + +UD_English-EWT Tokens 98.27[±0.13]% tokeparser_seq_C +UD_English-EWT Tokens 98.29[±0.07]% tokeparser_seq_E +UD_English-EWT Tokens 98.31[±0.10]% tokeparser_seq_F +UD_English-EWT Tokens 98.33[±0.07]% tokeparser_seq_D +UD_English-EWT Tokens 98.35[±0.11]% tokeparser_seq_A +UD_English-EWT Tokens 98.37[±0.06]% tokeparser_seq_B + +UD_English-EWT UAS 80.05[±0.30]% tokeparser_seq_E +UD_English-EWT UAS 80.18[±0.26]% tokeparser_seq_F +UD_English-EWT UAS 80.22[±0.21]% tokeparser_seq_C +UD_English-EWT UAS 80.22[±0.25]% tokeparser_seq_D +UD_English-EWT UAS 80.47[±0.48]% tokeparser_seq_A +UD_English-EWT UAS 80.51[±0.05]% tokeparser_seq_B + +UD_English-EWT UFeats 95.30[±0.08]% tokeparser_seq_C +UD_English-EWT UFeats 95.31[±0.12]% tokeparser_seq_F +UD_English-EWT UFeats 95.33[±0.06]% tokeparser_seq_D +UD_English-EWT UFeats 95.43[±0.08]% tokeparser_seq_A +UD_English-EWT UFeats 95.44[±0.09]% tokeparser_seq_B +UD_English-EWT UFeats 95.45[±0.09]% tokeparser_seq_E + +UD_English-EWT UPOS 93.93[±0.12]% tokeparser_seq_F +UD_English-EWT UPOS 94.07[±0.06]% tokeparser_seq_D +UD_English-EWT UPOS 94.08[±0.10]% tokeparser_seq_B +UD_English-EWT UPOS 94.11[±0.02]% tokeparser_seq_C +UD_English-EWT UPOS 94.13[±0.09]% tokeparser_seq_A +UD_English-EWT UPOS 94.23[±0.06]% tokeparser_seq_E + +UD_English-EWT Words 98.27[±0.13]% tokeparser_seq_C +UD_English-EWT Words 98.29[±0.07]% tokeparser_seq_E +UD_English-EWT Words 98.31[±0.10]% tokeparser_seq_F +UD_English-EWT Words 98.33[±0.07]% tokeparser_seq_D +UD_English-EWT Words 98.35[±0.11]% tokeparser_seq_A +UD_English-EWT Words 98.37[±0.06]% tokeparser_seq_B +-------------------------------------------------------------------------------- +UD_French-GSD LAS 84.76[±0.36]% tokeparser_seq_C +UD_French-GSD LAS 84.81[±0.22]% tokeparser_seq_A_CONTROL +UD_French-GSD LAS 85.00[±0.17]% tokeparser_seq_B +UD_French-GSD LAS 85.02[±0.18]% tokeparser_seq_E +UD_French-GSD LAS 85.17[±0.27]% tokeparser_seq_A +UD_French-GSD LAS 85.27[±0.22]% tokeparser_seq_D +UD_French-GSD LAS 85.44[±0.12]% tokeparser_seq_F + +UD_French-GSD Lemmas 97.48[±0.04]% tokeparser_seq_E +UD_French-GSD Lemmas 97.51[±0.03]% tokeparser_seq_D +UD_French-GSD Lemmas 97.51[±0.04]% tokeparser_seq_F +UD_French-GSD Lemmas 97.53[±0.05]% tokeparser_seq_C +UD_French-GSD Lemmas 97.54[±0.09]% tokeparser_seq_A_CONTROL +UD_French-GSD Lemmas 97.58[±0.07]% tokeparser_seq_B +UD_French-GSD Lemmas 97.66[±0.09]% tokeparser_seq_A + +UD_French-GSD Sentences 90.80[±0.72]% tokeparser_seq_A_CONTROL +UD_French-GSD Sentences 90.86[±0.65]% tokeparser_seq_E +UD_French-GSD Sentences 90.89[±0.26]% tokeparser_seq_B +UD_French-GSD Sentences 90.93[±0.67]% tokeparser_seq_A +UD_French-GSD Sentences 91.15[±0.33]% tokeparser_seq_D +UD_French-GSD Sentences 91.60[±0.46]% tokeparser_seq_F +UD_French-GSD Sentences 91.63[±0.56]% tokeparser_seq_C + +UD_French-GSD Tokens 99.43[±0.05]% tokeparser_seq_A +UD_French-GSD Tokens 99.43[±0.06]% tokeparser_seq_B +UD_French-GSD Tokens 99.44[±0.05]% tokeparser_seq_A_CONTROL +UD_French-GSD Tokens 99.46[±0.03]% tokeparser_seq_F +UD_French-GSD Tokens 99.47[±0.09]% tokeparser_seq_E +UD_French-GSD Tokens 99.49[±0.06]% tokeparser_seq_D +UD_French-GSD Tokens 99.56[±0.02]% tokeparser_seq_C + +UD_French-GSD UAS 87.37[±0.38]% tokeparser_seq_C +UD_French-GSD UAS 87.47[±0.35]% tokeparser_seq_A_CONTROL +UD_French-GSD UAS 87.52[±0.10]% tokeparser_seq_E +UD_French-GSD UAS 87.55[±0.20]% tokeparser_seq_B +UD_French-GSD UAS 87.74[±0.25]% tokeparser_seq_A +UD_French-GSD UAS 87.85[±0.13]% tokeparser_seq_D +UD_French-GSD UAS 88.00[±0.20]% tokeparser_seq_F + +UD_French-GSD UFeats 95.66[±0.04]% tokeparser_seq_C +UD_French-GSD UFeats 95.79[±0.08]% tokeparser_seq_E +UD_French-GSD UFeats 95.87[±0.05]% tokeparser_seq_D +UD_French-GSD UFeats 95.94[±0.04]% tokeparser_seq_B +UD_French-GSD UFeats 95.98[±0.07]% tokeparser_seq_F +UD_French-GSD UFeats 95.99[±0.11]% tokeparser_seq_A +UD_French-GSD UFeats 96.01[±0.11]% tokeparser_seq_A_CONTROL + +UD_French-GSD UPOS 96.95[±0.04]% tokeparser_seq_E +UD_French-GSD UPOS 96.96[±0.11]% tokeparser_seq_C +UD_French-GSD UPOS 97.03[±0.05]% tokeparser_seq_D +UD_French-GSD UPOS 97.05[±0.08]% tokeparser_seq_F +UD_French-GSD UPOS 97.07[±0.08]% tokeparser_seq_A_CONTROL +UD_French-GSD UPOS 97.11[±0.07]% tokeparser_seq_A +UD_French-GSD UPOS 97.15[±0.08]% tokeparser_seq_B + +UD_French-GSD Words 99.20[±0.07]% tokeparser_seq_A +UD_French-GSD Words 99.21[±0.05]% tokeparser_seq_B +UD_French-GSD Words 99.24[±0.02]% tokeparser_seq_F +UD_French-GSD Words 99.26[±0.03]% tokeparser_seq_A_CONTROL +UD_French-GSD Words 99.27[±0.06]% tokeparser_seq_E +UD_French-GSD Words 99.29[±0.06]% tokeparser_seq_D +UD_French-GSD Words 99.34[±0.03]% tokeparser_seq_C +-------------------------------------------------------------------------------- +UD_Norwegian-Bokmaal LAS 83.23[±0.09]% tokeparser_seq_A +UD_Norwegian-Bokmaal LAS 83.23[±0.12]% tokeparser_seq_B +UD_Norwegian-Bokmaal LAS 83.61[±0.15]% tokeparser_seq_F +UD_Norwegian-Bokmaal LAS 83.86[±0.16]% tokeparser_seq_D +UD_Norwegian-Bokmaal LAS 83.92[±0.07]% tokeparser_seq_C +UD_Norwegian-Bokmaal LAS 83.94[±0.07]% tokeparser_seq_E + +UD_Norwegian-Bokmaal Lemmas 96.41[±0.02]% tokeparser_seq_F +UD_Norwegian-Bokmaal Lemmas 96.44[±0.03]% tokeparser_seq_D +UD_Norwegian-Bokmaal Lemmas 96.46[±0.04]% tokeparser_seq_E +UD_Norwegian-Bokmaal Lemmas 96.55[±0.03]% tokeparser_seq_C +UD_Norwegian-Bokmaal Lemmas 96.60[±0.02]% tokeparser_seq_B +UD_Norwegian-Bokmaal Lemmas 96.62[±0.04]% tokeparser_seq_A + +UD_Norwegian-Bokmaal Sentences 94.27[±0.38]% tokeparser_seq_E +UD_Norwegian-Bokmaal Sentences 94.30[±0.35]% tokeparser_seq_B +UD_Norwegian-Bokmaal Sentences 94.66[±0.14]% tokeparser_seq_A +UD_Norwegian-Bokmaal Sentences 94.70[±0.15]% tokeparser_seq_C +UD_Norwegian-Bokmaal Sentences 94.85[±0.29]% tokeparser_seq_F +UD_Norwegian-Bokmaal Sentences 95.04[±0.12]% tokeparser_seq_D + +UD_Norwegian-Bokmaal Tokens 100.00% tokeparser_seq_A +UD_Norwegian-Bokmaal Tokens 100.00% tokeparser_seq_C +UD_Norwegian-Bokmaal Tokens 100.00% tokeparser_seq_E +UD_Norwegian-Bokmaal Tokens 100.00% tokeparser_seq_F +UD_Norwegian-Bokmaal Tokens 100.00[±0.00]% tokeparser_seq_D +UD_Norwegian-Bokmaal Tokens 99.99[±0.01]% tokeparser_seq_B + +UD_Norwegian-Bokmaal UAS 86.14[±0.09]% tokeparser_seq_A +UD_Norwegian-Bokmaal UAS 86.17[±0.09]% tokeparser_seq_B +UD_Norwegian-Bokmaal UAS 86.51[±0.13]% tokeparser_seq_F +UD_Norwegian-Bokmaal UAS 86.65[±0.12]% tokeparser_seq_D +UD_Norwegian-Bokmaal UAS 86.80[±0.09]% tokeparser_seq_E +UD_Norwegian-Bokmaal UAS 86.84[±0.08]% tokeparser_seq_C + +UD_Norwegian-Bokmaal UFeats 94.04[±0.08]% tokeparser_seq_D +UD_Norwegian-Bokmaal UFeats 94.18[±0.04]% tokeparser_seq_E +UD_Norwegian-Bokmaal UFeats 94.21[±0.04]% tokeparser_seq_B +UD_Norwegian-Bokmaal UFeats 94.21[±0.04]% tokeparser_seq_C +UD_Norwegian-Bokmaal UFeats 94.23[±0.02]% tokeparser_seq_A +UD_Norwegian-Bokmaal UFeats 94.23[±0.10]% tokeparser_seq_F + +UD_Norwegian-Bokmaal UPOS 96.20[±0.01]% tokeparser_seq_B +UD_Norwegian-Bokmaal UPOS 96.22[±0.07]% tokeparser_seq_F +UD_Norwegian-Bokmaal UPOS 96.24[±0.07]% tokeparser_seq_D +UD_Norwegian-Bokmaal UPOS 96.26[±0.02]% tokeparser_seq_A +UD_Norwegian-Bokmaal UPOS 96.38[±0.03]% tokeparser_seq_E +UD_Norwegian-Bokmaal UPOS 96.40[±0.04]% tokeparser_seq_C + +UD_Norwegian-Bokmaal Words 100.00% tokeparser_seq_A +UD_Norwegian-Bokmaal Words 100.00% tokeparser_seq_C +UD_Norwegian-Bokmaal Words 100.00% tokeparser_seq_E +UD_Norwegian-Bokmaal Words 100.00% tokeparser_seq_F +UD_Norwegian-Bokmaal Words 100.00[±0.00]% tokeparser_seq_D +UD_Norwegian-Bokmaal Words 99.99[±0.01]% tokeparser_seq_B +-------------------------------------------------------------------------------- +UD_Romanian-RRT LAS 80.27[±0.19]% tokeparser_seq_D +UD_Romanian-RRT LAS 80.31[±0.25]% tokeparser_seq_B +UD_Romanian-RRT LAS 80.59[±0.16]% tokeparser_seq_F +UD_Romanian-RRT LAS 80.61[±0.17]% tokeparser_seq_A +UD_Romanian-RRT LAS 80.62[±0.04]% tokeparser_seq_E +UD_Romanian-RRT LAS 80.81[±0.13]% tokeparser_seq_C + +UD_Romanian-RRT Lemmas 96.07[±0.04]% tokeparser_seq_F +UD_Romanian-RRT Lemmas 96.07[±0.06]% tokeparser_seq_E +UD_Romanian-RRT Lemmas 96.13[±0.09]% tokeparser_seq_B +UD_Romanian-RRT Lemmas 96.15[±0.09]% tokeparser_seq_D +UD_Romanian-RRT Lemmas 96.20[±0.04]% tokeparser_seq_C +UD_Romanian-RRT Lemmas 96.28[±0.07]% tokeparser_seq_A + +UD_Romanian-RRT Sentences 94.67[±1.07]% tokeparser_seq_B +UD_Romanian-RRT Sentences 95.09[±0.17]% tokeparser_seq_E +UD_Romanian-RRT Sentences 95.19[±0.60]% tokeparser_seq_D +UD_Romanian-RRT Sentences 95.21[±0.78]% tokeparser_seq_A +UD_Romanian-RRT Sentences 95.34[±0.16]% tokeparser_seq_C +UD_Romanian-RRT Sentences 96.11[±0.43]% tokeparser_seq_F + +UD_Romanian-RRT Tokens 99.46[±0.19]% tokeparser_seq_B +UD_Romanian-RRT Tokens 99.56[±0.11]% tokeparser_seq_E +UD_Romanian-RRT Tokens 99.57[±0.13]% tokeparser_seq_A +UD_Romanian-RRT Tokens 99.58[±0.05]% tokeparser_seq_D +UD_Romanian-RRT Tokens 99.61[±0.08]% tokeparser_seq_F +UD_Romanian-RRT Tokens 99.63[±0.07]% tokeparser_seq_C + +UD_Romanian-RRT UAS 85.66[±0.30]% tokeparser_seq_D +UD_Romanian-RRT UAS 85.80[±0.07]% tokeparser_seq_E +UD_Romanian-RRT UAS 85.80[±0.25]% tokeparser_seq_B +UD_Romanian-RRT UAS 85.93[±0.15]% tokeparser_seq_F +UD_Romanian-RRT UAS 86.02[±0.06]% tokeparser_seq_A +UD_Romanian-RRT UAS 86.15[±0.08]% tokeparser_seq_C + +UD_Romanian-RRT UFeats 95.72[±0.09]% tokeparser_seq_D +UD_Romanian-RRT UFeats 95.73[±0.10]% tokeparser_seq_B +UD_Romanian-RRT UFeats 95.75[±0.06]% tokeparser_seq_F +UD_Romanian-RRT UFeats 95.77[±0.20]% tokeparser_seq_E +UD_Romanian-RRT UFeats 95.80[±0.03]% tokeparser_seq_A +UD_Romanian-RRT UFeats 95.80[±0.04]% tokeparser_seq_C + +UD_Romanian-RRT UPOS 96.53[±0.10]% tokeparser_seq_B +UD_Romanian-RRT UPOS 96.59[±0.05]% tokeparser_seq_A +UD_Romanian-RRT UPOS 96.59[±0.05]% tokeparser_seq_F +UD_Romanian-RRT UPOS 96.59[±0.07]% tokeparser_seq_D +UD_Romanian-RRT UPOS 96.61[±0.01]% tokeparser_seq_C +UD_Romanian-RRT UPOS 96.70[±0.09]% tokeparser_seq_E + +UD_Romanian-RRT Words 99.46[±0.19]% tokeparser_seq_B +UD_Romanian-RRT Words 99.56[±0.11]% tokeparser_seq_E +UD_Romanian-RRT Words 99.57[±0.13]% tokeparser_seq_A +UD_Romanian-RRT Words 99.58[±0.05]% tokeparser_seq_D +UD_Romanian-RRT Words 99.61[±0.08]% tokeparser_seq_F +UD_Romanian-RRT Words 99.63[±0.07]% tokeparser_seq_C +-------------------------------------------------------------------------------- +UD_Turkish-IMST LAS 50.54[±2.36]% tokeparser_seq_F +UD_Turkish-IMST LAS 50.65[±1.21]% tokeparser_seq_E +UD_Turkish-IMST LAS 51.61[±0.95]% tokeparser_seq_B +UD_Turkish-IMST LAS 51.67[±0.35]% tokeparser_seq_D +UD_Turkish-IMST LAS 51.84[±0.70]% tokeparser_seq_A +UD_Turkish-IMST LAS 52.34[±0.27]% tokeparser_seq_C +UD_Turkish-IMST LAS 52.37[±0.59]% tokeparser_seq_A_CONTROL + +UD_Turkish-IMST Lemmas 84.41[±1.54]% tokeparser_seq_E +UD_Turkish-IMST Lemmas 85.43[±0.43]% tokeparser_seq_B +UD_Turkish-IMST Lemmas 85.45[±0.61]% tokeparser_seq_C +UD_Turkish-IMST Lemmas 85.61[±0.54]% tokeparser_seq_A +UD_Turkish-IMST Lemmas 85.63[±0.74]% tokeparser_seq_F +UD_Turkish-IMST Lemmas 86.03[±0.44]% tokeparser_seq_A_CONTROL +UD_Turkish-IMST Lemmas 86.12[±0.16]% tokeparser_seq_D + +UD_Turkish-IMST Sentences 94.58[±1.81]% tokeparser_seq_F +UD_Turkish-IMST Sentences 94.60[±0.94]% tokeparser_seq_C +UD_Turkish-IMST Sentences 94.84[±0.47]% tokeparser_seq_D +UD_Turkish-IMST Sentences 94.90[±0.46]% tokeparser_seq_B +UD_Turkish-IMST Sentences 95.47[±0.47]% tokeparser_seq_A_CONTROL +UD_Turkish-IMST Sentences 95.51[±0.65]% tokeparser_seq_E +UD_Turkish-IMST Sentences 95.96[±0.65]% tokeparser_seq_A + +UD_Turkish-IMST Tokens 97.57[±2.67]% tokeparser_seq_F +UD_Turkish-IMST Tokens 98.53[±0.80]% tokeparser_seq_D +UD_Turkish-IMST Tokens 98.63[±0.94]% tokeparser_seq_B +UD_Turkish-IMST Tokens 98.69[±0.70]% tokeparser_seq_E +UD_Turkish-IMST Tokens 98.88[±0.61]% tokeparser_seq_C +UD_Turkish-IMST Tokens 99.25[±0.31]% tokeparser_seq_A_CONTROL +UD_Turkish-IMST Tokens 99.34[±0.22]% tokeparser_seq_A + +UD_Turkish-IMST UAS 58.70[±1.24]% tokeparser_seq_E +UD_Turkish-IMST UAS 58.70[±2.60]% tokeparser_seq_F +UD_Turkish-IMST UAS 59.67[±0.56]% tokeparser_seq_D +UD_Turkish-IMST UAS 59.88[±0.96]% tokeparser_seq_B +UD_Turkish-IMST UAS 60.05[±0.29]% tokeparser_seq_A +UD_Turkish-IMST UAS 60.37[±0.16]% tokeparser_seq_C +UD_Turkish-IMST UAS 60.55[±0.28]% tokeparser_seq_A_CONTROL + +UD_Turkish-IMST UFeats 82.48[±0.49]% tokeparser_seq_A_CONTROL +UD_Turkish-IMST UFeats 82.81[±0.20]% tokeparser_seq_A +UD_Turkish-IMST UFeats 82.86[±0.19]% tokeparser_seq_B +UD_Turkish-IMST UFeats 82.86[±0.69]% tokeparser_seq_E +UD_Turkish-IMST UFeats 82.94[±0.55]% tokeparser_seq_D +UD_Turkish-IMST UFeats 82.99[±0.44]% tokeparser_seq_F +UD_Turkish-IMST UFeats 83.12[±0.29]% tokeparser_seq_C + +UD_Turkish-IMST UPOS 89.26[±0.20]% tokeparser_seq_B +UD_Turkish-IMST UPOS 89.31[±0.71]% tokeparser_seq_E +UD_Turkish-IMST UPOS 89.49[±0.66]% tokeparser_seq_A_CONTROL +UD_Turkish-IMST UPOS 89.50[±0.34]% tokeparser_seq_A +UD_Turkish-IMST UPOS 89.53[±0.46]% tokeparser_seq_C +UD_Turkish-IMST UPOS 89.59[±0.47]% tokeparser_seq_F +UD_Turkish-IMST UPOS 89.83[±0.49]% tokeparser_seq_D + +UD_Turkish-IMST Words 95.51[±2.55]% tokeparser_seq_F +UD_Turkish-IMST Words 96.47[±0.74]% tokeparser_seq_D +UD_Turkish-IMST Words 96.58[±0.87]% tokeparser_seq_B +UD_Turkish-IMST Words 96.63[±0.67]% tokeparser_seq_E +UD_Turkish-IMST Words 96.80[±0.59]% tokeparser_seq_C +UD_Turkish-IMST Words 97.15[±0.30]% tokeparser_seq_A_CONTROL +UD_Turkish-IMST Words 97.26[±0.21]% tokeparser_seq_A