Athena 2.0: Discourse and User Modeling in Open Domain Dialogue

no code implementations • 3 Aug 2023 • Omkar Patil, Lena Reed, Kevin K. Bowden, Juraj Juraska, Wen Cui, Vrindavan Harrison, Rishi Rajasekaran, Angela Ramirez, Cecilia Li, Eduardo Zamora, Phillip Lee, Jeshwanth Bheemanpally, Rohan Pandey, Adwait Ratnaparkhi, Marilyn Walker

Conversational agents are consistently growing in popularity and many people interact with them every day.

coreference-resolution named-entity-recognition +1

Controlling Personality Style in Dialogue with Zero-Shot Prompt-Based Learning

no code implementations • 8 Feb 2023 • Angela Ramirez, Mamon Alsalihy, Kartik Aggarwal, Cecilia Li, Liren Wu, Marilyn Walker

We also test whether NLG personality demonstrations from the restaurant domain can be used with meaning representations for the video game domain to generate personality stylized utterances about video games.

In-Context Learning Style Transfer +1

Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot

no code implementations • EMNLP (ACL) 2021 • Juraj Juraska, Kevin K. Bowden, Lena Reed, Vrindavan Harrison, Wen Cui, Omkar Patil, Rishi Rajasekaran, Angela Ramirez, Cecilia Li, Eduardo Zamora, Phillip Lee, Jeshwanth Bheemanpally, Rohan Pandey, Adwait Ratnaparkhi, Marilyn Walker

Athena 2. 0 is an Alexa Prize SocialBot that has been a finalist in the last two Alexa Prize Grand Challenges.

Dialogue Management Management

Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue

no code implementations • 15 Oct 2021 • Lena Reed, Cecilia Li, Angela Ramirez, Liren Wu, Marilyn Walker

We experiment with few-shot prompt-based learning, comparing GPT-Neo to Jurassic-1, for the movies, music, TV, sports, and video game domains, both within and cross-domain, with different prompt set sizes (2, 3, 10), formats, and meaning representations consisting of either sets of WikiData KG triples, or dialogue acts.

Hallucination Language Modelling +1