Showing cs.CLShow all
2 papers · 1 filter
cs.CL2018
A Study on Dialogue Reward Prediction for Open-Ended Conversational Agents
Heriberto Cuayáhuitl, Seonghan Ryu, Donghyeon Lee +1
The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled in…
cs.CL2018
Neural Sentence Embedding using Only In-domain Sentences for Out-of-domain Sentence Detection in Dialog Systems
Seonghan Ryu, Seokhwan Kim, Junhwi Choi +2
To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentence…