Prompt-based or in-context learning has achieved high zero-shot performance on many
natural language generation (NLG) tasks. Here we explore the performance of prompt …

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 …

This report describes Athena, a dialogue system for spoken conversation on popular topics
and current events. We develop a flexible topic-agnostic approach to dialogue management …

Human evaluation is becoming a necessity to test the performance of Chatbots. However, off-
the-shelf settings suffer the severe reliability and replication issues partly because of the …

Dialogue systems need to produce responses that realize multiple types of dialogue acts
(DAs) with high semantic fidelity. In the past, natural language generators (NLGs) for …

Athena 2.0 is an Alexa Prize SocialBot that has been a finalist in the last two Alexa Prize
Grand Challenges. One reason for Athena's success is its novel dialogue management …

One challenge with open-domain dialogue systems is the need to produce truthful, high-
quality responses on any topic. We aim to improve the quality and coverage of Athena, an …

Ontology merging is an important task in ontology engineering to date. However, despite the
efforts devoted to ontology merging, the incorporation of relevant features of ontologies such …

Every model is only as strong as the data that it is trained on. In this paper, we present a new
dataset, obtained by merging four publicly available annotated corpora for task-oriented …

Traditional statistical natural language generation (NLG) systems require substantial hand-
engineering: many of the components, such as content planners, sentence planners and …