Papers by Takayuki Yamamoto
Preference Estimation via Opponent Modeling in Multi-Agent Negotiation (2026.findings-acl)
Copied to clipboard
Yuta Konishi, Kento Yamamoto, Eisuke Sonomoto, Rikuho Takeda, Ryo Furukawa, Yusuke Muraki, Takafumi Shimizu, Kazuma Fukumura, Yuya Kanemoto, Takayuki Ito, Shiyao Ding
| Challenge: | Existing numerical-only approaches fail to capture qualitative information embedded in natural language interactions, resulting in unstable and incomplete preference estimation. |
| Approach: | They propose a preference estimation method that integrates natural language information into a Bayesian opponent modeling framework. |
| Outcome: | The proposed method improves agreement rate and preference estimation accuracy by integrating probabilistic reasoning with natural language understanding. |
Relation Prediction for Unseen-Entities Using Entity-Word Graphs (D19-53)
Copied to clipboard
Yuki Tagawa, Motoki Taniguchi, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma, Takayuki Yamamoto, Keiichi Nemoto
| Challenge: | Knowledge graphs (KGs) are incomplete and miss some information. |
| Approach: | They propose to learn entity representations via a graph structure that uses Seen-entities, Unseen-Entities and words as nodes created from the descriptions of all entities. |
| Outcome: | The proposed method improves relation prediction for the entity pairs containing Unseen-entities. |