Drawing from Conversation Analysis (CA), we examine how the orientation towards
progressivity in talk-keeping things moving-might help us better understand and design for …

We present two categories of model-agnostic adversarial strategies that reveal the
weaknesses of several generative, task-oriented dialogue models: Should-Not-Change …

While end-to-end neural conversation models have led to promising advances in reducing
hand-crafted features and errors induced by the traditional complex system architecture …

In modern interactive speech-based systems, speech is consumed and transcribed
incrementally prior to having disfluencies removed. This post-processing step is crucial for …

In dialogue, the addressee may initially misunderstand the speaker and respond
erroneously, often prompting the speaker to correct the misunderstanding in the next turn …

We investigate an end-to-end method for automatically inducing task-based dialogue
systems from small amounts of unannotated dialogue data. It combines an incremental …

Learning with minimal data is one of the key challenges in the development of practical,
production-ready goal-oriented dialogue systems. In a real-world enterprise setting where …

The ability to handle miscommunication is crucial to robust and faithful conversational AI.
People usually deal with miscommunication immediately as they detect it, using highly …

In this paper, we look at Natural Language Inference, arguing that the notion of inference the
current NLP systems are learning is much narrower compared to the range of inference …

Spontaneous spoken dialogue is often disfluent, containing pauses, hesitations, self-
corrections and false starts. Processing such phenomena is essential in understanding a …