The Stanford Natural Language Processing Group present some freely available tools and techniques that deliver state-of-the-art performance for Arabic processing tasks.
Software
- Stanford Arabic Parser - Download the full distribution, which includes a grammar trained on the most recent releases of the first three parts of the Penn Arabic Treebank (ATB). Arabic-specific parsing instructions, a FAQ, and a recommended train/dev/test split of the ATB are also available.
- Tregex/TregexGUI - A regular expression package for parse trees. Useful for browsing and searching the ATB. Supports Unicode (UTF-8) input and display.
- Stanford Arabic POS Tagger - Get the full distribution along with the trained Arabic tagger.
Aucun commentaire:
Enregistrer un commentaire