Archives For predictive chat

Chatting with robots absolutely fascinates me. I’ve received two telemarketing calls for secondary education that was merely voice-clips served by an algorithm based on my responses. But that wasn’t evident until about the 25 second mark. Pretty good 2015 Turing test! I got one into a 3 minute loop asking it weird things, actually.

Check this out…

Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require hand-crafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation.

Human: who is skywalker ?
Machine: he is a hero .
Human: who is bill clinton ?
Machine: he ’s a billionaire .
Human: is sky blue or black ?
Machine: blue .
Human: does a cat have a tail ?
Machine: yes .
Human: does a cat have a wing ?
Machine: no
Human: can a cat fly ?
Machine: no .
Human: how many legs does a cat have ?
Machine: four , i think .
Human: how many legs does a spider have ?
Machine: three , i think .
Human: how many legs does a centipede have ?
Machine: eight .
Human: what is the color of the sky ?
Machine: blue .
Human: what is the color of water ?
Machine: water .
Human: what is the color of blood ?
Machine: it is the same as a black eye .
Human: what is the usual color of a leaf ?
Machine: it is a green one .
Human: what is the color of a yellow car ?
Machine: yellow .
Human: how much is two plus two ?
Machine: four .
Human: how much is ten minus two ?
Machine: seventy – two .

via The Future of Neural Network-based Chatbots and Intelligent Virtual Agents: A Neural Conversational Model.

Advertisements