A Pytorch implementation of the BIST Parsers (for graph based parser only)

To be more accurate, this implementation is just a line-by-line translation from the DyNet implementation that can be found here. The techniques behind the parser are described in the paper Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations.

Required software

Python 2.7 interpreter
Pytorch library

Data format:

The software requires having a training.conll and development.conll files formatted according to the CoNLL data format, or a training.conllu and development.conllu files formatted according to the CoNLLU data format.

Train a parsing model

python src/parser.py --outdir [results directory] --train training.conll --dev development.conll --epochs 30 --lstmdims 125 --lstmlayers 2 [--extrn extrn.vectors] --bibi-lstm

Parse data with your parsing model

The command for parsing a test.conll file formatted according to the CoNLL data format with a previously trained model is:

python src/parser.py --predict --outdir [results directory] --test test.conll [--extrn extrn.vectors] --model [trained model file] --params [param file generate during training]

The parser will store the resulting conll file in the out directory (--outdir).

Difference from the DyNet implementation