Natural Language Processing: The Age of Transformers

Re:Natural Language Processing: The Age of Transformers by ArtWomb on Friday August 30, 2019 @08:31AM (#20837876)

Conversational AI is much closer than we think. Neural sequence-to-sequence models are successful in domain specific domains. But in the context of chit-chat based dialogue systems, the responses lack humanity. Undoubtedly due to the fact they don't comprehend our world. Transfer learning alleviates some of that awkwardness.

If anyone's interested in further experiments on their own. There is now a unified Python framework for dialogue models ;)

https://parl.ai/about/

[ Parent | on HN ]

Re:Natural Language Processing: The Age of Transformers by abhishek0318 on Friday August 30, 2019 @08:34AM (#20837902)

Really? Most of the chatbots in production are rule based systems.

[ Parent | on HN ]

Re:Natural Language Processing: The Age of Transformers by macawfish on Monday September 02, 2019 @02:05AM (#20857079)

The transformer can also be used at different levels of abstraction, e.g. to do interesting stuff with knowledge graphs. I think the transformer architecture is about to make things very, very interesting.

https://arxiv.org/pdf/1904.02342.pdf

[ Parent | on HN ]

Re:Natural Language Processing: The Age of Transformers by p1esk on Friday August 30, 2019 @12:05PM (#20839866)

We don’t even know how many breakthroughs it will take to get to the level of 3yo’s conversational abilities. And I’m talking major level breakthroughs, like LSTM or Transformer, probably trained on much more data.

[ Parent | on HN ]