We experiment with the conversation modeling task by casting it to a task of predicting the next sequence given the previous sequence or sequences using recurrent networks. We find that this approach can do surprisingly well on generating fluent and accurate replies to conversations.
We test the model on chat sessions from an IT helpdesk dataset of conversations, and find that the model can sometimes track the problem and provide a useful answer to the user. We also experiment with conversations obtained from a noisy dataset of movie subtitles, and find that the model can hold a natural conversation and sometimes perform simple forms of common sense reasoning. From a qualitative point of view, our model is sometimes able to produce natural conversations.
Human: where are you now ?
Machine: i ’m in the middle of nowhere .
Human: what is the purpose of dying ?
Machine: to have a life .
Human: what is the purpose of being intelligent ?
Machine: to find out what it is .
Human: what is the purpose of emotions ?
Machine: i don ’t know .
A Neural Conversational Model
Oriol Vinyals and Quoc V. Le
Google
http://arxiv.org/pdf/1506.05869v2.pdf
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 handcrafted 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. The strength of our model is that it can be trained end-to-end and thus requires much fewer hand-crafted rules. We find that this straightforward model can generate simple conversations given a large conversational training dataset. Our preliminary suggest that, despite optimizing the wrong objective function, the model is able to extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles. On a domain-specific IT helpdesk dataset, the model can find a solution to a technical problem via conversations. On a noisy open-domain movie transcript dataset, the model can perform simple forms of common sense reasoning. As expected, we also find that the lack of consistency is a common failure mode of our model.
VPN issues.
Describe your problem: i am having issues accessing vpn page and enter your name and password and check if its working fine now : )
Machine: hi
Human: hello
Machine: could you please let me know what are the operating systems you are using ?
Human: i am using linux
Machine: ok it was in the ssl vpn on which you stated it was broken
Machine: please check if you are logged in to corp network
Machine: what is the error that you are running please
Human: i am seeing an error related to vpn
Machine: what is the error message that you are getting when connecting to vpn using network connect ?
Human: connection refused or something like that
Machine: may i know the version of network connect you connect ?
Human: i am not sure i know that
Machine: is the network connect prompting for any user certificate ?
Human: yes
Machine: are you at home or at work at the moment ?
Machine: office ?
Human: i am at home
Machine: try this
Machine: goto
Human: done
Machine: try logging in with
Human: yes , now it works !
Machine: great
Machine: anything else that i can help
Human: no , that was very useful
Machine: you are other than
Machine: have a nice night
Philosophical Q&A
Human: what is the purpose of life ?
Machine: to serve the greater good .
Human: what is the purpose of living ?
Machine: to live forever .
Human: what is the purpose of existence ? Machine: to find out what happens when we get to the planet earth .
Human: where are you now ?
Machine: i ’m in the middle of nowhere .
Human: what is the purpose of dying ?
Machine: to have a life .
Human: what is the purpose of being intelligent ?
Machine: to find out what it is .
Human: what is the purpose of emotions ?
Machine: i don ’t know .