Features of the tool
- Highly customizable tool
- Language independent
- Multiplataform
- Free and open source
Input of the system
- Corpus in XML file (UTF-8)
- Optionally
- Existing dictionary (to upgrade)
- Configuration file (to customize the execution)
- Verbal list (to study a set of verbs)
Output of the system
- A file with lexicon dictionary for each verb studied
- A ID's dictionary file with ID's of sentences which was example of each pattern founded (if the corpus have the characteristic "ID")
- A statistic file of execution