We care about neural machine translation for several reasons.
1) Results show that NMT produces automatic translations that are significantly preferred by humans to other machine translation outputs. This has led several companies to switch NMT-based translation systems.
2) Similar methods (often called seq2seq) are also effective for many other NLP and language-related applications such as dialogue, image captioning, and summarization. A recent talk from HarvardNLP describing some of these recent advances is available here.
3) NMT has been used as a representative application of the recent success of deep learning-based artificial intelligence. For instance a recent NYT magazine cover story focused on Google’s NMT system.
We recommend starting with the ACL’16 NMT tutorial produced by researchers at Stanford and NYU. The tutorial also includes a detailed bibliography describing work in the field.
You just need two files: a source file and a target file. Each with one sentence per line with words space separated. These files can come from standard free translation corpora such a WMT, or it can be any other sources you want to train from.
While in theory you can train on any machine; in practice for all but trivally small data sets you will need a GPU that supports CUDA if you want training to finish in a reasonable amount of time. For medium-size models you will need at least 4GB; for full-size state-of-the-art models 8-12GB is recommend.
Follow the quick-start instructions on the Torch page.
You may also need to install the
luarocks install tds
Afterwards you can just checkout the repo and run.
First you need to install
wget -P /tmp https://github.com/NVIDIA/nvidia-docker/releases/download/v1.0.0-rc.3/nvidia-docker_1.0.0.rc.3-1_amd64.deb sudo dpkg -i /tmp/nvidia-docker*.deb
If this command does not work, you may need to run the following updates,
sudo apt-add-repository 'deb https://apt.dockerproject.org/repo ubuntu-xenial main' sudo apt-get update sudo apt-get install docker-engine nvidia-modprobe
Then simply run our Docker container
sudo nvidia-docker run -it harvardnlp/opennmt:8.0 .
Once in the instance, check out the latest code
git clone https://github.com/opennmt/opennmt.git
The best way to do this is through Docker. We have a public AMI with the preliminary
CUDA drivers installed:
ami-c12f86a1. Start a P2/G2 GPU instance with this AMI and
nvidia-docker command above to get started.
You can install OpenNMT as a library in the standard way,
luarocks make rocks/opennmt-scm-1.rockspec
We run a daily integration test of the system on EC2 to check that it is functioning properly. The logs of the system are publicly available in the integration test repo.
We have posted a complete tutorial for training a German-to-English translation system on standard data.
There are several different pretrained models available on the models page.
Try the OPUS Project. An open-source collection of parallel corpora. After stripping XML tags, you should be able to use the raw files directly in OpenNMT.
Yes. OpenNMT is a general-purpose attention-based seq2seq system. There is very little code that is translation specific, and so it should be effective for many of these applications.
For the case of summarization, OpenNMT has been shown to be more effective than neural systems like NAMAS, and will be supported going forward. See the models page for a pretrained summarization system on the Gigaword dataset.
Partially. OpenNMT can be extended with additional Torch neural networks, and a bit of coding. As an example, we have implemented a relatively general-purpose im2text system, with a small amount of additional code. Feel free to use this as a model for extending OpenNMT.
That would be great. Just be sure to read the
STYLE.md before you submit.
We are normally in our Gitter channel. If you want to contribute come chat. We are friendly.
That’s not really a question, but we would love to add that feature! The quickest way to get it into OpenNMT is to send us a pull request on GitHub. Just fork the repo, make the change, and click send pull request.
Okay, that’s fine, we can help implement it. Go to our forum and add a feature request. We will get to it soon.