fenss / PyTorch_Biaffine_Dependency_Parsing

Biaffine Dependency Parsing based on PyTorch

PyTorch Biaffine Dependency Parsing

A re-implementation of Deep Biaffine Attention for Neural Dependency Parsing based on PyTorch.

Requirement

Python  == 3.6  
PyTorch == 1.0.1
Cuda == 9.0

Usage

modify the config file, detail see the Config directory
Train:
(1) sh run_train_p.sh
(2) python -u main.py --config ./Config/config.cfg --device cuda:0--train -p 
    [device: "cpu", "cuda:0", "cuda:1", ......]

Performance

Data/score	UAS	LAS
CTB51	90.20	88.83
PTB	---	---

Reference

• Deep Biaffine Attention for Neural Dependency Parsing
• https://github.com/tdozat/Parser-v3
• https://github.com/zhangmeishan/BiaffineDParser

Question

• if you have any question, you can open a issue or email bamtercelboo@{gmail.com, 163.com}.

• if you have any good suggestions, you can PR or email me.