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

Competition 2: German


Table: The obtained average precision (AP%) in the information retrieval task for the submitted segmentations in German. Methods without authors are reference methods by the organizers. Indexing is performed using Okapi (BM25) weighting for all morphemes except the most common ones (stoplist) with frequency higher than 150,000. Asterisk (*) denotes submissions that did not include segmentations for Competition 2 and were evaluated by using the smaller Competition 1 wordlist
AUTHOR METHOD AP%
- TWOL first 0.4885
- TWOL all 0.4743
- Morfessor Baseline 0.4656
- Morfessor CatMAP 0.4642
Monson et al. ParaMor-Morfessor Mimic 0.4490
Monson et al. ParaMor-Morfessor Union 0.4478
Virpioja & Kohonen Allomorfessor 0.4388
Can & Manandhar 1 0.4006*
Lavellée & Langlais RALI-COF 0.3965*
Can & Manandhar 2 0.3952*
- snowball german 0.3865
Lignos et al. - 0.3863*
Monson et al. ParaMor Mimic 0.3757
Tchoukalov et al. MetaMorph 0.3752*
Spiegler et al. PROMODES committee 0.3634*
- dummy 0.3509
Golénia et al. UNGRADE 0.3496*
Spiegler et al. PROMODES 0.3484*
- grammatical first 0.3353
Lavellée & Langlais RALI-ANA 0.3284*
Bernhard MorphoNet 0.3167
- grammatical all 0.3014
Spiegler et al. PROMODES 2 0.2997*

Return to the result page

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

You are at: CIS → Unsupervised Morpheme Analysis -- Morpho Challenge 2009

Page maintained by webmaster at cis.hut.fi, last updated Monday, 07-Sep-2009 13:14:55 EEST