Active learning
Implementation of the active learning protocol from A User Study of the Incremental Learning in NMT based on the toolkit OpenNMT-py. It was built in PyTorch.

Interactive Neural Machine Translation
A fork of the OpenNMT-py toolkit implementing several interactive machine translation protocols. It was built in PyTorch.

Online demonstrator
Online demonstrator of several applications of machine translation for the processing of historical documents. The server is based on NMT-Keras.

Prefix-based IMT
Extension of Barrachina et al. implementation of the prefix-based interactive machine translation protocol. Taken a Moses search graph as an input, this software generates a word graph compatible with Barrachina et al. software and runs a user simulation. It was built in Python.

Segment-based IMT
Implementation of the segment-based interactive machine translation protocol from Segment-based Interactive-Predictive Machine Translation. It was built in Python profiting from Moses’ XML scheme.

Statistical dictionary
Given a parallel data set, this software trains an statistical dictionary for translating documents. It was built in Python and makes use of mgiza for computing IBM model 1 alignments.

Word-Level AutoCompletion
A fork of theOpenNMT-py toolkit that deploys a word-level autocompletion tool. It was built in PyTorch.