All Projects → hankcs → Id Cnn Cws

hankcs / Id Cnn Cws

Licence: gpl-3.0
Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Id Cnn Cws

Etagger
reference tensorflow code for named entity tagging
Stars: ✭ 100 (-22.48%)
Mutual labels:  cnn, crf
End To End Sequence Labeling Via Bi Directional Lstm Cnns Crf Tutorial
Tutorial for End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Stars: ✭ 87 (-32.56%)
Mutual labels:  cnn, crf
Ncrfpp
NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
Stars: ✭ 1,767 (+1269.77%)
Mutual labels:  cnn, crf
Min nlp practice
Chinese & English Cws Pos Ner Entity Recognition implement using CNN bi-directional lstm and crf model with char embedding.基于字向量的CNN池化双向BiLSTM与CRF模型的网络,可能一体化的完成中文和英文分词,词性标注,实体识别。主要包括原始文本数据,数据转换,训练脚本,预训练模型,可用于序列标注研究.注意:唯一需要实现的逻辑是将用户数据转化为序列模型。分词准确率约为93%,词性标注准确率约为90%,实体标注(在本样本上)约为85%。
Stars: ✭ 107 (-17.05%)
Mutual labels:  cnn, crf
Captcha
基于CNN的验证码整体识别
Stars: ✭ 125 (-3.1%)
Mutual labels:  cnn
Multilstm
keras attentional bi-LSTM-CRF for Joint NLU (slot-filling and intent detection) with ATIS
Stars: ✭ 122 (-5.43%)
Mutual labels:  crf
Ner
命名体识别(NER)综述-论文-模型-代码(BiLSTM-CRF/BERT-CRF)-竞赛资源总结-随时更新
Stars: ✭ 118 (-8.53%)
Mutual labels:  crf
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (-6.98%)
Mutual labels:  cnn
Asr syllable
基于卷积神经网络的语音识别声学模型的研究
Stars: ✭ 127 (-1.55%)
Mutual labels:  cnn
Motionblur Detection By Cnn
Stars: ✭ 126 (-2.33%)
Mutual labels:  cnn
Cnn Inference Engine Quick View
A quick view of high-performance convolution neural networks (CNNs) inference engines on mobile devices.
Stars: ✭ 124 (-3.88%)
Mutual labels:  cnn
What Is My Girlfriend Thinking
用 Tensorflow.js 猜猜我的女朋友在想什么. A Tensorflow.js application for facial classification.
Stars: ✭ 122 (-5.43%)
Mutual labels:  cnn
Libfacedetection
An open source library for face detection in images. The face detection speed can reach 1000FPS.
Stars: ✭ 10,852 (+8312.4%)
Mutual labels:  cnn
Unified Gesture And Fingertip Detection
A Unified Convolutional Neural Network Approach of Gesture Recognition and Fingertip Detection.
Stars: ✭ 121 (-6.2%)
Mutual labels:  cnn
Mylearn
machine learning algorithm
Stars: ✭ 125 (-3.1%)
Mutual labels:  crf
Daguan 2019 rank9
datagrand 2019 information extraction competition rank9
Stars: ✭ 121 (-6.2%)
Mutual labels:  crf
Deeplearning python
Deep Learning--深度学习
Stars: ✭ 123 (-4.65%)
Mutual labels:  cnn
Semantic Segmentation Of Remote Sensing Images
遥感图像的语义分割,基于深度学习,在Tensorflow框架下,利用TF.Keras,运行环境TF2.0+
Stars: ✭ 125 (-3.1%)
Mutual labels:  crf
Pytorch Sift
PyTorch implementation of SIFT descriptor
Stars: ✭ 123 (-4.65%)
Mutual labels:  cnn
A Convolutional Recurrent Neural Network For Real Time Speech Enhancement
A minimum unofficial implementation of the "A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement" (CRN) using PyTorch
Stars: ✭ 123 (-4.65%)
Mutual labels:  cnn

ID-CNN-CWS

Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation".

2017-10-20_13-23-31

It implements the following 4 models for CWS:

  • Bi-LSTM
  • Bi-LSTM-CRF
  • ID-CNN
  • ID-CNN-CRF

Dependencies

  • Python >= 3.6
  • TensorFlow >= 1.2

Both CPU and GPU are supported. GPU training is 10 times faster.

Preparation

Run following script to convert corpus to TensorFlow dataset.

$ ./scripts/make.sh

Train and Test

Quick Start

$ ./scripts/run.sh $dataset $model
  • $dataset can be pku, msr, asSC or cityuSC.
  • $model can be cnn or bilstm.

For example:

$ ./scripts/run.sh pku cnn

It will train a cnn model on pku dataset, then evaluate performance on test set.

CRF Layer

To enable CRF layer, simply append --viterbi to your command, e.g.

$ ./scripts/run.sh pku cnn --viterbi

Accuracy

2017-10-20_13-25-11

Speed

2017-10-20_11-44-42

Acknowledgments

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].