Feature Request List

(srush) #1

Pinned Thread of Feature Requests (v0.6 is next release)


  • Residual Connections
  • Batch Normalization (v0.6)
  • Convolution encoder (v0.6)
  • Complex encoders (v0.6)
  • Sequence tagging (v0.6)

Data sets / Models

  • Dialogue/Chatbot
  • Core NLP (tagging/parsing)


  • RL Training (v0.6)
  • Interactive RL
  • seq2seq speech
  • Other encoder memory structures


  • Integrate Im2Text (v0.6)
  • Better word embedding support (v0.6)
  • Training Scheduler
  • Support for SGM test/train (v0.6)

(srush) #2

(Wabbit) #3

There are several applications where the user can provide implicit feedback about the quality of a translation (though they may not provide the ground truth translation) through their behavior E.g: accept or reject the translation, click or not click etc. Think of a webapp which uses a translation service as a backend.

This paper Learning to Search Better Than Your Teacher provides a way to start from some reference translation and improve it through exploration while providing localy optimality guarantees.

In essence it is middle ground between pure RL and fully supervised learning.
@srush I think it’ll be a good addition to the OpenNMT toolkit and we could use an RNN as the Oracle in this case. What do you feel?

(srush) #4

There is another thread about some of this. I think we will get to it, but it is pretty low-pri unless someone takes an interest in implementing.

(Wabbit) #5

I think it’s an important problem since the language that we use is changing constantly. Getting human generated translations will be difficult at scale.

I can help implementing it. How do I create a proposal-what process do you follow?

(srush) #6

Wabbit are you in our gitter channel? https://gitter.im/OpenNMT/openmt maybe a good place to discuss.

First thing is to figure out a general purpose way to add RL training to the core code, likely will have to discuss with @guillaumekln and others.

(srush) #7

(srush) #8

(Netxiao) #9

I think direct output the original unk word to the results is needed.

(srush) #10

Can you be more specific?

(Netxiao) #11

in my old translate system(Moses), unknown words are copied verbatim to the output.
in openNMT, when I translate a sentence, often give the wrong unk word in the results,especially if the first vocabulary is unk.

for example:
src sentences:
bitterness fed on the man who had made the world laugh .
the bitterness is unk word, will got wrong result:
fed on on . 的 人
the bitterness has been lost in result.

@guillaumekln give me explain, but I think It is very important for a practical system.

(Etienne Monneret) #12

It’s certainly due to the attn layer that makes a bad word alignment between the source and the translation. It’s one of the reasons why I asked for more explanations on its functioning, and the way to tune it, here:

(srush) #13

Yup, I get it now. This is not a “simple” problem, we actually have to look into research for doing this better. We will try to find something reasonable to implement.

(Shivali ) #14

I have very limited human translated data and have been reading about RL. Would like to work on it ! Please suggest some good reading materials !

Also, is there a way to fine tune OpenNMT’s model ? To limit backpropagation while retraining?