Ben Bolte

This seems like a Keras issue. After the new updates Gandlf is totally broken, though... It's disheartening

Your formula probably wouldn't work because `max_r` indicates the index of the maximum similarity answer in `d['good']`, not the actual value in `d['good']` (i.e. `np.max`). I guess `max_r` should really...

It is a small change in the Keras source code (set the `supports_masking` class variable in the Lambda layer to True instead of False). Otherwise there isn't a way to...

ah yeah merge doesn't support masking yet, you can use this pull request -> https://github.com/fchollet/keras/pull/2413

Oh I'm not sure. To be honest, I've been messing around with stuff a lot and it's far from cohesive. I can't tell much from the error report... You might...

I didn't reproduce the results from the paper, I'm not sure how they got the results they did. I wondered if they just let it train for a really long...

Oh sure! Hmm... The major thing was using a bunch of dimensions, I found 1000 embedding dimensions worked well (no word2vec pretraining). I think [this commit](https://github.com/codekansas/keras-language-modeling/blob/51223f2ec2262a0e4f614df24125c31e4aaf6e29/insurance_qa_eval.py) has the right parameters...

I get the error too, I'm not sure why it happens (has happened in other Keras projects). I will change the master branch back (changed it originally without testing it)

The loss function is a hinge loss, i.e. `loss = margin - cos(question, good_answer) + cos(question, bad_answer)` where `cos` is the cosine similarity between the two things. We're trying to...

@mossaab0 Each model is highly dependent on the parameters you pass it and how long you train it for. I've messed around with them a lot and the parameters in...