Offline reinforcement learning (RL) allows agents to learn effective,
re...
Pre-trained models with dual and cross encoders have shown remarkable su...
Recent years have seen an increasing trend in the volume of personal med...
People capture photos and videos to relive and share memories of persona...
Contextualizing language technologies beyond a single language kindled
e...
Learning task-oriented dialog policies via reinforcement learning typica...
As task-oriented dialog systems are becoming increasingly popular in our...
While deep learning through empirical risk minimization (ERM) has succee...
MultiWOZ is one of the most popular multi-domain task-oriented dialog
da...
We present a new corpus for the Situated and Interactive Multimodal
Conv...
A video-grounded dialogue system is required to understand both dialogue...
This paper introduces the Ninth Dialog System Technology Challenge (DSTC...
Motivated by the needs of resource constrained dialog policy learning, w...
Next generation virtual assistants are envisioned to handle multimodal i...
As digital virtual assistants become ubiquitous, it becomes increasingly...
An automated metric to evaluate dialogue quality is vital for optimizing...
Modern virtual personal assistants provide a convenient interface for
co...
Matching pursuit (MP) methods are a promising class of feature construct...
We consider the problem of efficiently learning optimal control policies...