Multi-decoder setup for multi-task learning

OpenNMT / OpenNMT-tf

Neural machine translation and sequence learning using TensorFlow

https://opennmt.net/

MIT License

1.46k stars 392 forks source link

Multi-decoder setup for multi-task learning #130

Open guillaumekln opened 6 years ago

guillaumekln commented 6 years ago

Similarly to the ParallelEncoder, a ParallelDecoder setup could allow multi-task learning. This should not be too hard to implement but we need to take care of some details:

support separate values for the decoding parameters (beam_width, length_penalty, etc.),
parts of SequenceToSequence assume a single output head (e.g. loss computation, reverse vocabulary lookup, exported outputs for model serving, etc. which should be moved in the decoder itself)

BigFishMaster commented 5 years ago

@guillaumekln Do you have a plan to implement ParallelDecoder?

guillaumekln commented 5 years ago

I don't have plan to work on this at the moment.

sarubi commented 4 years ago

@guillaumekln is there any possibility on OpenNMT-py to integrate multi encoder decoders setup for multi-task learning? If so I wish to contribute for it.

guillaumekln commented 4 years ago

This issue is for OpenNMT-tf. If you wish to contribute the feature for OpenNMT-py, can you update the issue you opened there?

sarubi commented 4 years ago

@guillaumekln updated on OpenNMT-py.