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

Competition 1: Finnish


Table: The submitted unsupervised morpheme analysis compared to the Gold Standard in Finnish (Competition 1).
AUTHOR METHOD PRECISION RECALL F-MEASURE
Monson Paramor+Morfessor 49.76% 47.25% 48.47%
Morfessor MAP 76.83% 27.54% 40.55%
Monson Paramor 46.40% 34.44% 39.53%
Monson Morfessor 77.40% 21.52% 33.68%
Zeman 1 58.51% 20.47% 30.33%
Morfessor baseline 88.82% 12.01% 21.16%
Kohonen et al - 92.55% 6.89% 12.82%
Zeman 3 72.41% 3.42% 6.54%


Table: Corresponding results in the Morpho Challenge 2007 (for reference)
AUTHOR METHOD PRECISION RECALL F-MEASURE
Bernhard 2 59.65% 40.44% 48.20%
morfessor MAP 76.83% 27.54% 40.55%
Bernhard 1 75.99% 25.01% 37.63%
Bordag 5a 71.32% 24.40% 36.36%
Bordag 5 71.72% 23.61% 35.52%
Zeman - 58.84% 20.92% 30.87%
McNamee 3 45.53% 8.56% 14.41%
McNamee 4 68.09% 5.68% 10.49%
McNamee 5 86.69% 3.35% 6.45%

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 17:24:41 EEST