Knowledge-based authentication is crucial for task-oriented spoken dialo...
We present NLU++, a novel dataset for natural language understanding (NL...
Transformer-based pretrained language models (PLMs) offer unmatched
perf...
Transformer-based language models (LMs) pretrained on large text collect...
Building conversational systems in new domains and with added functional...
General-purpose pretrained sentence encoders such as BERT are not ideal ...
We present PolyResponse, a conversational search engine that supports
ta...
Despite their popularity in the chatbot literature, retrieval-based mode...
Progress in Machine Learning is often driven by the availability of larg...
Statistical spoken dialogue systems usually rely on a single- or multi-d...
Cross-domain natural language generation (NLG) is still a difficult task...
Even though machine learning has become the major scene in dialogue rese...
This paper presents two ways of dealing with scarce data in semantic dec...
User Simulators are one of the major tools that enable offline training ...
Reinforcement learning (RL) is a promising approach to solve dialogue po...
Dialogue assistants are rapidly becoming an indispensable daily aid. To ...
Reinforcement learning is widely used for dialogue policy optimization w...
Human conversation is inherently complex, often spanning many different
...