Sockeye

Added
- Added nbest list reranking options using isometric translation criteria as proposed in an ICASSP 2021 paper https://arxiv.org/abs/2110.03847.
To use this feature pass a criterion (`isometric-ratio, isometric-diff, isometric-lc`) when specifying `--metric`.
- Added `--output-best-non-blank` to output non-blank best hypothesis from the nbest list.

Fixed

- Fix type of valid_length to be pt.Tensor instead of Optional[pt.Tensor] = None for jit tracing

Added
- Added the implementation of Neural vocabulary selection to Sockeye as presented in our NAACL 2022 paper "The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation" (Tobias Domhan, Eva Hasler, Ke Tran, Sony Trenous, Bill Byrne and Felix Hieber).
- To use NVS simply specify `--neural-vocab-selection` to `sockeye-train`. This will train a model with Neural Vocabulary Selection that is automatically used by `sockeye-translate`. If you want look at translations without vocabulary selection specify `--skip-nvs` as an argument to `sockeye-translate`.

Added

- Added `sockeye-train` argument `--no-reload-on-learning-rate-reduce` that disables reloading the best training checkpoint when reducing the learning rate. This currently only applies to the `plateau-reduce` learning rate scheduler since other schedulers do not reload checkpoints.

Fixed

- Fix scoring with batches of size 1 (whic may occur when `|data| % batch_size == 1`.

Fixed

- When resuming training with a fully trained model, `sockeye-train` will correctly exit without creating a duplicate (but separately numbered) checkpoint.