Algraeph is a tool for manual alignment of linguistic graphs, such as phrase structure trees or dependency structures.
Graphs are read from one or more graphbanks (or treebanks). Algraeph currently supports graphs in the general GraphML format and in the Alpino format (for Dutch). Alignment relations are user-defined. The alignments are stored in a simple XML format, which can be used for further processing. The result - a parallel graph corpus - is a useful data set for many tasks in computational linguistics and natural language processing such as automatic summarization, automatic translation, paraphrase extraction, recognizing textual entailment, etc.
The Algraeph project is implemented in the Python programming language using the wxPython GUI toolkit. It has been tested on Mac OS X, GNU Linux and MS Windows, but should run on any platform which is supported by Python, wxPython and Graphviz.
- Read graphs from graphbanks in the general GraphML format or in Alpino XML format.
- Render pairs of graphs, align their nodes, and label the alignments according to a user-defined set of alignment relations.
- Add text comments to aligned graph pairs
- Set graph viewing options, for example, collapse or expand arbitray parts of a graph.
- Save aligned graphs to an image file in any format supported by Graphviz (png, gif, jpg, ps, dot, etc).
- Cross-platform: runs on any platform which is supported byPython, wxPython, and Graphviz, including Mac OS X, GNU Linux and MS Windows
- Open source: licensed under the GNU Public License
- Free: provided free of charge