Applications that could benefit from automatic understanding of human-human
conversations often come with challenges associated with private information in real-world …

Collecting high quality conversational data can be very expensive for most applications and
infeasible for others due to privacy, ethical, or similar concerns. A promising direction to …

Traditional goal-oriented dialogue systems rely on various components such as natural
language understanding, dialogue state tracking, policy learning and response generation …

We propose Machines Talking To Machines (M2M), a framework combining automation and
crowdsourcing to rapidly bootstrap end-to-end dialogue agents for goal-oriented dialogues …

We present the third iteration of Chirpy Cardinal, an open-domain dialogue agent developed
for the Alexa Prize Socialbot Grand Challenge 5 (SGC5) competition. 1 In 2023, while pure …

Machine learning approaches for building task-oriented dialogue systems require large
conversational datasets with labels to train on. We are interested in building task-oriented …

Summarizing sales calls is a routine task performed manually by salespeople. We present a
production system which combines generative models fine-tuned for customer-agent setting …

Being able to reply with a related, fluent, and informative response is an indispensable
requirement for building high-quality conversational agents. In order to generate better …

Abstract We introduce Doc2Dial, an end-to-end framework for generating conversational
data grounded in given documents. It takes the documents as input and generates the …

The rise of big data has amplified the need for efficient, user-friendly automated machine
learning (AutoML) tools. However, the intricacy of understanding domain-specific data and …