深度学习>> End-to-end-Sequence-Labeling-via-Bi-directional-LSTM-CNNs-CRF-Tutorial>> 返回
项目作者： xjtuerz0

项目描述 ：
BiLSTM, CRF, NER
高级语言： Jupyter Notebook
项目地址: git://github.com/xjtuerz0/End-to-end-Sequence-Labeling-via-Bi-directional-LSTM-CNNs-CRF-Tutorial.git


End-to-end-Sequence-Labeling-via-Bi-directional-LSTM-CNNs-CRF-Tutorial

This is a PyTorch tutorial for the ACL’16 paper
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

This repository includes

  • IPython Notebook of the tutorial
  • Data folder
  • Setup Instructions file
  • Pretrained models directory (The notebook will automatically download pre-trained models into this directory, as required)

Authors

Anirudh Ganesh

Peddamail Jayavardhan Reddy

Installation

The best way to install pytorch is via the pytorch webpage

Setup

Creating new Conda environment

conda create -n pytorch python=3.5

Activate the condo environment

source activate pytorch

Setting up notebooks with specific python version (python 3.5)

  1. conda install notebook ipykernel
  2. ipython kernel install --user

PyTorch Installation command:

conda install pytorch torchvision -c pytorch

NumPy installation

conda install -c anaconda numpy

Download GloVe vectors and extract glove.6B.100d.txt into “./data/“ folder

wget http://nlp.stanford.edu/data/glove.6B.zip

Data Files

You can download the data files from within this repo over here