11 comments

[ 3.8 ms ] story [ 81.4 ms ] thread
Hey guys.

Don’t expect accurate answers here - it’s an experimental weekend hack.

With this experiment, we wanted to understand how we could train a neural network on new external datasets very quickly and study the difference in the language and answers depending on the topic of the dataset.

No scripted chatbot here, we are talking of neural-nets trained in the wild :) We are using the celebrated seq-2-seq model which computes a “thought-vector” from an input sentence and generates an output sentence conditioned on this vector. We gathered various datasets from stackexchange and launched a big overnight training of our models to have some surreal morning coffee talks with our AI.

There’s still a ton of work for the answers to start to make sense (longer training and bigger datasets would improve the quality of course, we can also easily add components to improve the variety and coherence of the responses) but a difference can definitely be noticed based on the dataset subset.

This will allow us to test a variety of new datasets way faster than before. Let us know what you think, and if you think of a cool dataset to test, just let us know on Github.

Do you have any details on your experience training the models? Was this using vanilla RNNs, LSTM cells, did you use an attention mechanism, etc.? How long did you train for?
It can enter a loop easely. Gamer girl vs. me

me: yes

gg: I'll send screen shots

me: yes

gg: I'll send screen shots

me: yes

gg: I'll send screen shots

me: yes

gg: I'll send screen shots

....

Responses to a specific message are deterministic in this model (no diversity promoting objective implemented) so this is to be expected :)
Q: "How many electrons in an atom of Lithium?" A: "Of course not!" - Physics expert
Honestly, this gives such irrelevant answers, it might as well be random. The presentation is pretty cool but it doesn't actually work well at all.
Right now, it doesn't work at all. Would be great to test and iterate on it a bit and to have some sense to the answers before exposing it to the world.
me: ruby on rails

Full Stack Dev: Do n't do this

Them: Yo! Does it compile?

Me: Yes

Them: I'll update the tag

Me: Ok thank you

Them: The second one then.