Etienne Monneret

Hi, ModernMT is storing your model in the "engines" subfolder and some temporary data in the "runtime" subfolder. If a previous storing exists, it tries to start from last state,...

The whole number of words, is less than twice the number of words in the 16M original sentences. Here is a quite complex example (also showing how I'm doing some...

A RNN is not learning phrases like a SMT. It is learning words sequences, on both encoder and decoder layers = what is the more probable word N after having...

I used our own tool. We are specialists of such a technical stuff. See for example our historical software Similis (now free).

For your information: after few real tests, our translators are impressed by the quality of the new model, trained with this new chunk enriched data. I'm now working on 2...

Thanks ! I give it a try right now ! :) For your question, all is said on this sentence in my original post: "I had the idea to extract...

Of course.. as the chunk pairs are added to the training data, they are also used by MMT in its online adaptation, like the original sentence pairs.

Yes : 16M sentence pairs + 50M chunk pairs (my new algo is a bit more selective than the first one), all in the training data. To avoid too fast...

I did 2 things: 1) I improved my chunking/pairing algo, and rejected chunk pairs with a too low quality estimation 2) I used the chunking covering to build an estimation...

Yes. You should finally get this: