opennmt/server

This project is considered obsolete as the Torch framework is no longer maintained. If you are starting a new project, please use an alternative in the OpenNMT family: OpenNMT-tf (TensorFlow) or OpenNMT-py (PyTorch) depending on your requirements.

OpenNMT: Open-Source Neural Machine Translation

OpenNMT is a full-featured, open-source (MIT) neural machine translation system utilizing the Torch mathematical toolkit.

The system is designed to be simple to use and easy to extend, while maintaining efficiency and state-of-the-art translation accuracy. Features include:

• Speed and memory optimizations for high-performance GPU training.
• Simple general-purpose interface, only requires and source/target data files.
• C++ implementation of the translator for easy deployment.
• Extensions to allow other sequence generation tasks such as summarization and image captioning.

Installation

OpenNMT only requires a Torch installation with few dependencies.

1. Install Torch
2. Install additional packages:

luarocks install tds
luarocks install bit32 # if using LuaJIT

For other installation methods including Docker, visit the documentation.

Quickstart

OpenNMT consists of three commands:

1. Preprocess the data.

th preprocess.lua -train_src data/src-train.txt -train_tgt data/tgt-train.txt -valid_src data/src-val.txt -valid_tgt data/tgt-val.txt -save_data data/demo

2. Train the model.

th train.lua -data data/demo-train.t7 -save_model model

3. Translate sentences.

th translate.lua -model model_final.t7 -src data/src-test.txt -output pred.txt

For more details, visit the documentation.

Citation

A technical report on OpenNMT is available. If you use the system for academic work, please cite:

@ARTICLE{2017opennmt,
  author = {{Klein}, G. and {Kim}, Y. and {Deng}, Y. and {Senellart}, J. and {Rush}, A.~M.},
  title = "{OpenNMT: Open-Source Toolkit for Neural Machine Translation}",
  journal = {ArXiv e-prints},
  eprint = {1701.02810}
}

Acknowledgments

Our implementation utilizes code from the following:

• Andrej Karpathy's char-rnn repo
• Wojciech Zaremba's lstm repo
• Element rnn library

Additional resources

• Documentation
• Forum
• Gitter channel

server's Issues

How to use the translation server?

Dear OpennMT Team,

Please excuse my asking. How can I actually run the server with a test model from the OpenNMT website and perform translations?

Thanks!

Rest Server issue: source text is sent but no translation is returned

Hi Alexander,

It took me a while to figure out how to run the Rest server and I used your Flask server http://github.com/OpenNMT/Server/

As you can see in the screen shot, it seems that the source text is sent, but no translation is returned either in the terminal or the web page. Any idea why?

I tested it first with source 'word', then the sentence "You can print all files directly.', but nothing is returned.

Here is a screen shot

https://www.dropbox.com/s/1b3k9a3nri6oj9w/opennmt.PNG?dl=0

Thanks in advance for your support.

Kind regards,
Mohamed

I hope my work could help you.

I have write one simple web app based on your code, and I hope it could help you now.
I'm not good at web, there are my rough project.
And maybe you could visit a sample here.

undefined symbol: lua_tointeger

Hi there! I'm using lua 5.2 because of out of the memory in lua 5.1 when preprocessing. But after installing zmq, the error is undefined symbol: lua_tointeger and zmq is installed in lua 5.1. How can I solve it? Here is error:
th> require("zmq")
/home/zyyt/torch/install/share/lua/5.2/trepl/init.lua:389: error loading module 'zmq' from file '/usr/local/lib/lua/5.1/zmq.so':
/usr/local/lib/lua/5.1/zmq.so: undefined symbol: lua_tointeger
stack traceback:
/home/zyyt/torch/install/share/lua/5.2/trepl/init.lua:506: in function </home/zyyt/torch/install/share/lua/5.2/trepl/init.lua:499>
[C]: in function 'error'
/home/zyyt/torch/install/share/lua/5.2/trepl/init.lua:389: in function 'require'
[string "_RESULT={require("zmq")}"]:1: in main chunk
[C]: in function 'xpcall'
/home/zyyt/torch/install/share/lua/5.2/trepl/init.lua:661: in function 'repl'
...zyyt/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:199: in main chunk
[C]: in ?

Is there anyway to enable -replace_unk when running the server?

I got the server to run which is great! But now I get if my model doesn't know what a word is. I found out about -replace_unk to get around this but how can I turn this on while runnig the model as a server?