Giter Club home page Giter Club logo

dependencyparser's Introduction

implement of "A Fast and Accurate Dependency Parser using Neural Networks "

0. 环境

  • python 3.6
  • pytorch 1.1.0

1. run code

  • prepare_data.py: 此文件为数据预处理过程

  • train the model : python main.py --mode train

  • 训练完成后,将模型拷贝至./data/model文件夹,并命名为model.pt

  • test the model: python main.py --mode test


2. 实验记录

  • 2019.05.03

在word embedding后加入dropout

test
UAS 81.3

  • 2019.04.30

修改激活函数、超参数

加入正则化

activation function : relu

optimization : Adagrad(lr=0.01,weight_decay=1e-8)

test
UAS 79.1

  • 2019.4.29

修改特征抽取函数

activation function : cube

batch size :2048

test
UAS 77.6

  • 2019.4.25

activation function:relu

optimization : mini-batched Adam

dropout : 0.5

hidden size : 200

batch size ; 1024

word embedding size : 100

pretrained word embedding : glove

test
UAS 74.1

dependencyparser's People

Contributors

zturbox avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.