Home

Awesome

debug seq2seq

Note: the repository is not maintained. Feel free to PM me if you'd like to take up the maintainance.

Make seq2seq for keras work. And also give a try to some other implementations of seq2seq.

The code includes:

Warning

Papers

Nice picture

seq2seq

Setup&Run

git clone https://github.com/nicolas-ivanov/debug_seq2seq
cd debug_seq2seq
bash bin/setup.sh
python bin/train.py

and then

python bin/test.py

Results

No good results were achieved so far:

[why ?] -> [i ' . . $$$ . $$$ $$$ $$$ $$$ as as as as i i]
[who ?] -> [i ' . . $$$ . $$$ $$$ $$$ $$$ as as as as i i]
[yeah ?] -> [i ' . . $$$ . $$$ $$$ $$$ $$$ as as as as i i]
[what is it ?] -> [i ' . . $$$ . $$$ $$$ $$$ $$$ as as as as as i]
[why not ?] -> [i ' . . $$$ . $$$ $$$ $$$ $$$ as as as as i i]
[really ?] -> [i ' . . $$$ . $$$ $$$ $$$ $$$ as as as as i i]

My guess is that there are some foundational problems in this approach:

are you a human?			-- no .
are you a robot or human?	-- no .
are you a robot?			-- no .
are you better than siri?  		-- yes .
are you here ?				-- yes .
are you human?			-- no .
are you really better than siri?	-- yes .
are you there 				-- you ' re not going to be
are you there?!?!			-- yes .

Not to mislead you: these results were achieved on a different seq2seq architecture, based on tensorflow.

Sampling with temperature could be used in order to diversify the output results, however that's again should be done inside seq2seq library.