Skip to content
Symphony Machine Translation
Branch: master
Clone or download
Latest commit 4d434a9 Jan 13, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
configurations
docs
experiments/src/main
mt
project
.gitignore
.jvmopts Minor edits. Jan 14, 2019
LICENSE
README.md
build.sbt [MODELS] Minor edits. Dec 3, 2018
version.sbt Updated the license. Jan 15, 2018

README.md

Symphony Machine Translation

We plan to soon publish a documentation website with information on how to use this software package. For now, we provide some instructions on how to reproduce the experiments presented in our paper, soon to be presented at EMNLP 2018, Contextual Parameter Generation for Universal Neural Machine Translation, Emmanouil A. Platanios, Mrinmaya Sachan, Graham Neubig, and Tom M. Mitchell.

Running Experiments

In order to reproduce our experimental results you must first execute sbt assembly on the root directory of this repository, after cloning it.

Example experiment scripts are located in the scripts directory. We will soon update this with the specific scripts used to reproduce the experiments presented in our paper.

Using Precompiled TensorFlow Distribution

In order to use the precompiled TensorFlow binaries that TensorFlow Scala provides, you need to change line 76 in the build.sbt file, from this:

libraryDependencies += "org.platanios" %% "tensorflow" % tensorFlowScalaVersion

to this:

libraryDependencies += "org.platanios" %% "tensorflow" % tensorFlowScalaVersion classifier "linux-cpu-x86_64"

Make sure to replace linux-cpu-x86_64 with the string that corresponds to your platform. Currently supported platforms are: linux-cpu-x86_64, linux-gpu-x86_64, and darwin-cpu-x86_64.

For more information on how to install/configure TensorFlow Scala, please refer to the official website.

TODOs

  • Add support for separate source/target word embeddings.
  • Add support for bridges between the encoder and the decoder (inspired from OpenNMT).
  • Add support for merging the bidirectional encoder states using either summation or concatenation.
  • Add support for other attention models, as in here.
  • Add support for scheduled sampling, presented in this paper.
You can’t perform that action at this time.