RoshanRane / RST-parser

End-to-end automatic RST parser using neural networks. This team-project is developed as part of the Masters course ANLP at the University of Potsdam.

RST-parser

An automatic RST parser implemented using neural networks. This team-project is done as part of the Masters course ANLP at the University of Potsdam. The parser is trained and tested on wall-street-journal corpus.

The whole project is divided into 2 sections :

1. Segmentation
2. Parsing

Files :

1. RST-00-corpus-reader : Contains Feature extractions for the Segmentor Neural Network
2. RST-01-EDU-segmenter : Segmentor implementation and results.
3. RST-02-parser : Feature extraction for Parsing and Parser results.
4. rst.py : Parser implementation

The guide to use each notebook is provided in the notebook itself.