Next generation task-oriented dialog systems need to understand conversational contexts
with their perceived surroundings, to effectively help users in the real-world multimodal …

Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety
of task-oriented dialogue domains without the expense of collecting in-domain data. In this …

This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This
edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct …

Conversational recommendation system (CRS) attracts increasing attention in various
application domains such as retail and travel. It offers an effective way to capture users' …

Task-oriented dialogue (ToD) benchmarks provide an important avenue to measure
progress and develop better conversational agents. However, existing datasets for end-to …

With the recent development of deep learning, AI models are widely used in various
domains. AI models show good performance for definite tasks such as image classification …

As humans, we experience the world with all our senses or modalities (sound, sight, touch,
smell, and taste). We use these modalities, particularly sight and touch, to convey and …

Abstract Knowledge bases (KBs) are usually essential for building practical dialogue
systems. Recently we have seen rapidly growing interest in integrating knowledge bases …

Recent data-driven conversational models are able to return fluent, consistent, and
informative responses to many kinds of requests and utterances in task-oriented scenarios …

Building an AI assistant that can seamlessly converse and instruct humans, in a user-centric
situated scenario, requires several essential abilities:(1) spatial and temporal understanding …