Biaffine Parser

This repo is to replicate the model in the paper Deep Biaffine Attention for Neural Dependency Parsing.

Currently, on the CoNLL09 English Dataset, I fall behind 1-2 points on UAS/LAS.

CoNLL09-English	UAS	LAS
Valid	93.52	90.16
Test	94.22	91.68
Original	95.21	93.20

Need more tuning for these models.

Quick Start

• This repo is based on my own framework bpase. You can git clone that repo and then

  python setup.py install
  

  to install the library. There might be some dependency problems that I did not fix yet.
• Quick Start

  python main.py 
  

  The model will be saved in saves.
• Test

  python test.py --trained_model saves/name_of_model
  

• Evaluation

  Convert output to conll format with ConvertToConll.ipynb
  perl eval.pl -q -b -g results/conll.test -s results/conll.test.pred -o test.scores