| |
|
|
|
|
|
Download and reference guide
- TiMBL
v.6.2.1 is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public
License (version 3) as published by the Free
Software Foundation.
- NEW: Debian, RPM, and Fink packages released for 64 bits architectures at http://apt.ticc.uvt.nl - see this page for more instructions
-
Book: Memory-Based Language
Processing - Daelemans, W., and Van den Bosch,
A. (2005). Cambridge, UK: Cambridge University Press.
- Reference
Guide (66 pages, 487 kB PDF); Daelemans, W.,
Zavrel, J., Van der Sloot, K., and Van den Bosch, A. (2009). TiMBL:
Tilburg Memory Based Learner, version 6.2, Reference Guide. ILK
Research Group Technical Report Series no. 09-01.
- API
guide (34 pages, 124 kB PDF); Van der Sloot,
K. (2009). TiMBL: Tilburg Memory Based Learner, version 6.2, API
Guide. ILK Research Group Technical Report Series no. 09-02.
Features
- Fast, decision-tree-based implementation of k-nearest neighbor classification
- Implementations of IB1 and IB2, IGTree, TRIBL, and TRIBL2 algorithms
- Similarity metrics: Overlap, MVDM, Jeffrey Divergence, Dot product, Cosine
- Feature weighting metrics: information gain, gain ratio, chi squared, shared variance
- Per-value similarity metrics: Levenshtein, Dice coefficient
- Distance weighting metrics: inverse, inverse linear, exponential decay
- Extensive verbosity options to inspect nearest neighbor sets
- Server functionality and extensive API
- Fast leave-one-out testing and internal cross-validation
- Handles user-defined example weighting
|
|
|
|
|
|
|
|
|
|
|
|
Additional TiMBL resources
| Dimbl |
Parallel TiMBL for multi-CPU machines |
| Mbt |
Memory-based tagger/generator |
| Tadpole |
Dutch morphosyntactic tagger |
| paramsearch |
Automatic parameter optimization for TiMBL (and other ML algorithms) |
| Timpute |
TiMBL-based data imputation |
| python-timbl |
Python language binding for TiMBL |
| rtimbl |
a Ruby interface to TiMBL |
| knngraph |
Visualizes nearest neighbors in a TiMBL instance base |
|
|
|
|
|
|
|
|
|
|
|
Registration and feedback
If you want to be informed about future TiMBL releases, please send an
email to timbl@uvt.nl.
Also, please send your questions and bug reports to timbl@uvt.nl. The development
of Timbl benefits from your contributions.
|
|
|
|
|
|
|
|
ILK Home
