Takanori Takebe — accepted AI-conference papers

2026

QuMAB: Query-based Multi-annotator Behavior Pattern Learning

Liyun Zhang, Zheng Lian, Hong Liu, Takanori Takebe, Shozo Nishii, Yuta Nakashima

AAAI 2026technical

Multi-annotator learning traditionally aggregates diverse annotations to approximate a single “ground truth”, treating disagreements as noise. However, this paradigm faces fundamental challenges: subjective tasks often lack absolute ground truth, and sparse annotation coverage makes aggregation stat

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

SimLabel: Similarity-Weighted Semi-supervision for Multi-annotator Learning with Missing Labels

Liyun Zhang, Zheng Lian, Hong Liu, Takanori Takebe, Yuta Nakashima

AAAI 2026technical

Multi-annotator learning (MAL) aims to model annotator-specific labeling patterns. However, existing methods face a critical challenge: they simply skip updating annotator-specific model parameters when encountering missing labels—a common scenario in real-world crowdsourced datasets where each anno

Cited by 0 Source ↗PDF ↗Scholar ↗