Nerve machine translation (NMT) open source tools

Blog address: http: //blog.csdn.net/wangxinginnlp/article/details/52944432

 


Tool Name: T2T: Tensor2Tensor Transformers

Address: https: //github.com/tensorflow/tensor2tensor

Language: Python / Tensorflow

Description: ★★★★★ five stars

https://research.googleblog.com/2017/06/accelerating-deep-learning-research.html

 

 

Tool Name: dl4mt

Address: https: //github.com/nyu-dl/dl4mt-tutorial/tree/master/session2

Language: Python / Theano

Summary:

Attention-based encoder-decoder model for machine translation.  

Dr. New York University Kyunghyun Cho group of developers.

 

Tool Name: blocks

Address: https: //github.com/mila-udem/blocks

Language: Python / Theano

Summary:

Blocks is a framework that helps you build neural network models on top of Theano. 

Université de Montréal LISA Lab (Laboratory Director Yoshua Bengio, laboratory now known as MILA Lab, home page: https: //mila.umontreal.ca/en/) development, before GroundHog (https://github.com/lisa -groundhog / GroundHog) upgrade alternative version.

 

 

Tool Name: EUREKA-MangoNMT

Address: https: //github.com/jiajunzhangnlp/EUREKA-MangoNMT

Language: C ++ 

简介:A C++ toolkit for neural machine translation for CPU. 

Dr. Zhang Jiajun Chinese Academy of Sciences Institute of Automation, Speech and Language Technology Research Group (http://www.nlpr.ia.ac.cn/cip/jjzhang.htm) development.

 

Tool Name: Nematus 

Address: https: //github.com/EdinburghNLP/nematus

Language: Python / Theano

Description: The University of Edinburgh published NMT tool

 

Tool Name: AmuNMT

Address: https: //github.com/emjotde/amunmt

Language: C ++ 

Summary:

A C++ inference engine for Neural Machine Translation (NMT) models trained with Theano-based scripts from Nematus (https://github.com/rsennrich/nematus) or DL4MT (https://github.com/nyu-dl/dl4mt-tutorial).

Moses Machine Translation CIC company Dr. Hieu Hoang (http://statmt.org/~s0565741/), who developed.

 

Tool Name: Zoph_RNN

Address: https: //github.com/isi-nlp/Zoph_RNN

Language: C ++

Summary:

A C++/CUDA toolkit for training sequence and sequence-to-sequence models across multiple GPUs.

USC Information Sciences Institute development.

 


Tool Name: sequence-to-sequence mdoels in tensorflow

Address: https: //www.tensorflow.org/versions/r0.11/tutorials/seq2seq/index.html

Language: TensorFlow / Python

简介:Sequence-to-Sequence Models

 

Tool Name: nmt_stanford_nlp

Address: http: //nlp.stanford.edu/projects/nmt/

Language: Matlab

Summary:

Neural machine translation (NMT) at Stanford NLP group.

 

Tool Name: OpenNMT

Address: http: //opennmt.net/

Languages: Lua / Torch

Summary:

OpenNMT was originally developed by Yoon Kim and harvardnlp.

 

Tool Name: lamtram

Address: https: //github.com/neubig/lamtram

Language: C ++ / DyNet

Summary:

lamtram: A toolkit for language and translation modeling using neural networks.

Dr. CMU Graham Neubig group of developers.

 

Tool Name: Neural Monkey

Address: https: //github.com/ufal/neuralmonkey

Language: TensorFlow / Python

简介:The Neural Monkey package provides a higher level abstraction for sequential neural network models, most prominently in Natural Language Processing (NLP). It is built on TensorFlow. It can be used for fast prototyping of sequential models in NLP which can be used e.g. for neural machine translation or sentence classification.

Institute of Formal and Applied Linguistics at Charles University 开发。

(WMT in NEURAL MT TRAINING TASK use is Neural Monkey See: http: //www.statmt.org/wmt17/)

 


Tool Name: Neural Machine Translation (seq2seq) Tutorial

Address: https: //github.com/tensorflow/nmt

Language: python / Tensorflow

Summary:

Google Brain's Dr. Luong Thang who produced

 

 

If you are interested in this tool, you can use the bilingual corpus WMT16 ran the play, corpus address http://www.statmt.org/wmt16/translation-task.html.
---------------------
Author: warrioR_wx
Source: CSDN
Original: https: //blog.csdn.net/wangxinginnlp/article/details/52944432
Disclaimer: This article as a blogger original article, reproduced, please attach Bowen link!

Guess you like

Origin www.cnblogs.com/jfdwd/p/11058614.html