Name
Abstract | ||
|---|---|---|
Abstract: Vector representation of legal documents is still the best way for computing classification clusters and labelling of its contents. A very special problem occurs with self organising maps: strong clusters tend to dominate neighbouring smaller clusters in terms of their weight vector structure, which influences the labels extracted from these. This unwelcome side-effect can be overcome efficiently with a dedicated fine-tuning phase at the end of the training process, in which the neighbourhood radius of the training function is set to zero. Experiments with our text collection have shown the high improvement of the quality of labelling. |
Year | DOI | Venue |
|---|---|---|
2001 | 10.1109/DEXA.2001.953155 | DEXA Workshop |
Keywords | Field | DocType |
high improvement,legal document,neighbourhood radius,dedicated fine-tuning phase,smaller cluster,self-organising maps,vector representation,classification cluster,weight vector structure,training process,training function,classification,side effect,boolean functions,information retrieval,learning artificial intelligence,world wide web,law,internet,search engines,html,labeling,fine tuning | Cluster (physics),Data mining,Pattern clustering,Computer science,Fine-tuning,Weight,Neighbourhood (mathematics),Document handling,Self organising maps,Law administration | Conference |
ISBN | Citations | PageRank |
0-7695-1230-5 | 0 | 0.34 |
References | Authors | |
14 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Erich Schweighofer | 1 | 250 | 32.37 |
| Andreas Rauber | 2 | 1925 | 216.21 |
| Michael Dittenbach | 3 | 297 | 26.48 |