Uri Alon

Asymetric context and model = 1, leads to saving only context instead of word vec

9

Hi, I'm a CS M.Sc. student from the Technion, Israel, researching applications of word vectors to programming language. Thanks for your code, it's great. I think there is a bug,...

Hi, `truncation='do_not_truncate'` is not working equivalently to `truncation=False`. When using `truncation=False` and provoding `max_length`, it defaults to `'longest_first'` truncation strategy. Whether this default behavior is natural or not, isn't `False`...

Hi, Is there a bug in GraphInference::DisplayGraph or is it supposed to be this way? The score of every edge is returned as the **sum of scores of all the...

Unneeded ReLU in Transformer-match

2

Hi, Thank you for sharing this great repository! I think that the ReLU in the k/q/v projections is unneeded, or at least, inconsistent with the Transformer paper: [https://github.com/hanxiao/tf-nlp-blocks/blob/master/nlp/match_blocks.py?fbclid=IwAR0HdDwaSpPZbhwi6BfzWY0P0ZIMOWAobZU5aPtvpZO2d3MTOEXrwkQzY5A#L113 ](https://github.com/hanxiao/tf-nlp-blocks/blob/master/nlp/match_blocks.py?fbclid=IwAR0HdDwaSpPZbhwi6BfzWY0P0ZIMOWAobZU5aPtvpZO2d3MTOEXrwkQzY5A#L113 )...