Laboratory of Computer and Information Science / Neural Networks Research Centre CIS Lab Helsinki University of Technology

Competition 1: German


Table: The submitted unsupervised morpheme analysis compared to the Gold Standard in German (Competition 1).
AUTHOR METHOD PRECISION RECALL F-MEASURE
Monson Paramor+Morfessor 49.53% 59.51% 54.06%
Morfessor MAP 67.56% 36.92% 47.75%
Monson Morfessor 67.16% 36.83% 47.57%
Monson Paramor 53.42% 38.15% 44.51%
Zeman 1 53.12% 28.37% 36.98%
Morfessor baseline 80.23% 19.22% 31.01%
Kohonen et al - 87.92% 7.44% 13.71%
Zeman 3 72.27% 7.15% 13.01%


Table: Corresponding results in the Morpho Challenge 2007 (for reference)
AUTHOR METHOD PRECISION RECALL F-MEASURE
Monson Paramor-Morfessor 51.45% 55.55% 53.42%
Bernhard 2 49.08% 57.35% 52.89%
Bordag 5a 60.45% 41.57% 49.27%
Bordag 5 60.71% 40.58% 48.64%
morfessor MAP 67.56% 36.92% 47.75%
Monson Morfessor 67.16% 36.83% 47.57%
Bernhard 1 63.20% 37.69% 47.22%
Monson ParaMor 59.05% 32.81% 42.19%
Zeman - 52.79% 28.46% 36.98%
McNamee 3 45.78% 9.28% 15.43%
McNamee 4 75.62% 6.67% 12.26%
McNamee 5 90.92% 4.21% 8.04%

Return to the result page

HOME | RULES | SCHEDULE | DATASETS | EVALUATION | WORKSHOP | RESULTS | FAQ | CONTACT

You are at: CIS → Unsupervised Morpheme Analysis -- Morpho Challenge 2008

Page maintained by webmaster at cis.hut.fi, last updated Wednesday, 09-Jul-2008 17:24:54 EEST