Added - Pre-training the RNN decoder. Usage: 1. Train with flag `--decoder-only`. 2. Feed identical source/target training data.
1.18.30
Fixed - Preserving max output length for each sentence to allow having identical translations for both with and without batching.
1.18.29
Changed - No longer restrict the vocabulary to 50,000 words by default, but rather create the vocabulary from all words which occur at least `--word-min-count` times. Specifying `--num-words` explicitly will still lead to a restricted vocabulary.
1.18.28
Not secure
Changed - Temporarily fixing the pyyaml version to 3.12 as version 4.1 introduced some backwards incompatible changes.
1.18.27
Fixed - Fix silent failing of NDArray splits during inference by using a version that always returns a list. This was causing incorrect behavior when using lexicon restriction and batch inference with a single source factor.
1.18.26
Added - ROUGE score evaluation. It can be used as the stopping criterion for tasks such as summarization.