Saya Kanno — accepted AI-conference papers

2023

PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives

Silin Gao, Beatriz Borges, Soyoung Oh, Deniz Bayazit, Saya Kanno, Hiromi Wakaki +2

ACL 2023long

Sustaining coherent and engaging narratives requires dialogue or storytelling agents to understandhow the personas of speakers or listeners ground the narrative. Specifically, these agents must infer personas of their listeners to produce statements that cater to their interests. They must also lear…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗

2022

ComFact: A Benchmark for Linking Contextual Commonsense Knowledge

Silin Gao, Jena D. Hwang, Saya Kanno, Hiromi Wakaki, Yuki Mitsufuji, Antoine Bosselut

EMNLP 2022finding

Understanding rich narratives, such as dialogues and stories, often requires natural language processing systems to access relevant knowledge from commonsense knowledge graphs. However, these systems typically retrieve facts from KGs using simple heuristics that disregard the complex challenges of i…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗