Marc-André Cournoyer

@svenwoldt that's a great idea! However, we don't have a good metric for measuring the quality of the model yet. #38 adds a validation set, maybe adding a tests set...

Ooops! Autoclosed indeed.

Yes it might be the reason. But restricting based on frequency ends up being a lot more difficult to implement. Since you have to rewrite all the examples because word...

Awesome work as always! I'm currently running /w `th train.lua --cuda --hiddenSize 1000 --numLayers 2 --dataset 30000 --vocabSize 10000` and will update with results.

Results after `th train.lua --cuda --hiddenSize 1000 --numLayers 2 --dataset 30000 --vocabSize 10000` for 50 epoch: ``` Epoch stats: Errors: min= 1.298625054104 max= 3.8777817894112 median= 2.3050528590272 mean= 2.3216041151624 std= 0.32521225826956...

Even if it overfits the data, don't you find it suspect that the eval always returns the same exact output? On master, when evaluating, I get a different output for...

@chenb67 thx for the fix and the paper! Will check it out. I'm re-training w/ this and will see.

Something definitely happened in this branch or recently on master that decreased the (subjective) quality of the responses in `eval.th`. It might be in the recent changes I pushed on...

@pothibo did you get it working? If you got a working config, I'll integrate it into Thin.

> Instead, I want to get to the point where `to_liquid` takes a context, so that not only would context setting overhead be isolated to drops, but it would also...