Scholar
Jason Naradowsky
Google Scholar ID: w4d5WRcAAAAJ
Researcher, Square Enix AI & Arts Alchemy
Citations & Impact
Citations
1,997
H-index
11
i10-index
13
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- Published multiple papers such as 'Mind the gap between conversations for improved long-term dialogue generation' (EMNLP Findings 2023) and 'Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models' (ACL Findings 2023). Contributed to open-source software projects like Wolfe and NLTK.
Research Experience
- Worked at Japanese AI/Robotics startup Preferred Networks; was a faculty research scientist at Johns Hopkins University; involved in the development of Wolfe, a probabilistic programming language; implemented a suite of dependency parsers for the Natural Language Toolkit (NLTK) during Google Summer of Code 2008 under the supervision of Sebastian Riedel and Jason Baldridge.
Education
- Completed PhD in Computer Science at UMass Amherst under David Smith and Mark Johnson; did postdoctoral work at the University of Cambridge with Anna Korhonen and at University College London with Sebastian Riedel.
Background
- Currently a researcher at Square Enix AI & Arts Alchemy, working towards ML-powered next generation interactive experiences in gaming. Also a project assistant professor at University of Tokyo, Miyao-ken, leading the dialogue and LLM group. Research interests include generative/LLM agents, character-driven dialogue generation and storytelling, analyzing LLM behavior and hallucinations (circuit analysis), emergent communication and situated language learning/multi-agent collaborative communication. Recently increasingly interested in computational creativity and the potential for AI in music creation.
Miscellany
- Erdős–Bacon number is arguably no greater than 8.
Co-authors