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

Competition 1: English


Table: The submitted unsupervised morpheme analysis compared to the Gold Standard in English (Competition 1).
AUTHOR METHOD PRECISION RECALL F-MEASURE
Monson Paramor-Morfessor 50.64% 63.30% 56.26%
Morfessor baseline 71.93% 43.27% 54.04%
Monson ParaMor 58.50% 48.10% 52.79%
Morfessor MAP 82.17% 33.08% 47.17%
Monson Morfessor 77.22% 33.95% 47.16%
Zeman 1 52.98% 42.07% 46.90%
Kohonen et al - 83.39% 13.43% 23.13%
Zeman 3 76.92% 8.47% 15.27%


Table: Corresponding results in the Morpho Challenge 2007 (for reference)
AUTHOR METHOD PRECISION RECALL F-MEASURE
Bernhard 2 61.63% 60.01% 60.81%
Bernhard 1 72.05% 52.47% 60.72%
Pitler - 74.73% 40.62% 52.63%
Monson Paramor-Morfessor 41.58% 65.08% 50.74%
Monson ParaMor 48.46% 52.95% 50.61%
morfessor MAP 82.17% 33.08% 47.17%
Monson Morfessor 77.22% 33.95% 47.16%
Zeman - 52.98% 42.07% 46.90%
Bordag 5a 59.69% 32.12% 41.77%
Bordag 5 59.80% 31.50% 41.27%
McNamee 3 43.47% 17.55% 25.01%
McNamee 4 75.96% 13.67% 23.17%
McNamee 5 92.34% 7.38% 13.67%

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 17:24:16 EEST