0:00:15hi everybody and then attention from cmu this the joint work done with my colleagues
0:00:20and one vice the mixing and so they might talk is going to talk about
0:00:23how to making a charity slot filling systems using the encoder decoder models
0:00:30so the slot filling system is the focus of this talk and it has been
0:00:34a device critically in recent years because we have better models more data
0:00:39but the is the one limitation of a just a two-pass approach is most of
0:00:45the proposed approach is sometimes of dialogue system is the with domain specific and it
0:00:50is restricted to one type of dialogue act states and there is not very domain-dependent
0:00:56so because of that we have difficulty of extending existing operating system
0:01:00when you don't lengths on your skills
0:01:03and a second difficulties sometime in a way deploy a system in real life this
0:01:08always out-of-domain a request and it's gonna be very limited to handling those out-of-domain request
0:01:16so our goal is we want to develop a domain general system that is not
0:01:21restricted to a the define predefine acts of state even this task
0:01:26and the encoder-decoder model things a promising a choice because it's a very powerful and
0:01:32its prosody model and it has been successfully applied to translation and the open domain
0:01:38so the idea is quite simple we have a encoder that encodes the dialogue history
0:01:42and of generating a dialog state representation and we have a decoder that you called
0:01:48the system responds spoken by token