Research at the Interaction Lab focuses on human-agent communication using
conversational Natural Language. The ultimate goal is to create systems where humans and …

Counterfactual Learning to Rank (LTR) methods optimize ranking systems using logged
user interactions that contain interaction biases. Existing methods are only unbiased if users …

Current neural network-based conversational models lack diversity and generate boring
responses to open-ended utterances. Priors such as persona, emotion, or topic provide …

Neural generative dialogue agents have shown an increasing ability to hold short chitchat
conversations, when evaluated by crowdworkers in controlled settings. However, their …

We study improving social conversational agents by learning from natural dialogue between
users and a deployed model, without extra annotations. To implicitly measure the quality of a …

This concise text provides an accessible introduction to artificial intelligence and intelligent
user interfaces (IUIs) and how they are at the heart of a communication revolution for …

Ranking systems form the basis for online search engines and recommendation services.
They process large collections of items, for instance web pages or e-commerce products …

Suicide prevention hotline counselors aid individuals during difficult times through millions
of calls and chats. A chatbot cannot safely replace a counselor, but we explore whether a …

Conversational agents are consistently growing in popularity and many people interact with
them every day. While many conversational agents act as personal assistants, they can …

Effective evaluation methods remain a significant challenge for research on open-domain
conversational dialogue systems. Explicit satisfaction ratings can be elicited from users, but …