News

The following paper has been accepted at Practical ML for Low Resource Settings Workshop (PM4LRS) @ ICLR 2024.

• Sota Nemoto, Shunsuke Kitada, and Hitoshi Iyatomi. “Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition”

A special issue of Journal of JSAI on doctoral dissertations, including a summary of my dissertation, is now available: https://www.jstage.jst.go.jp/article/jjsai/39/1/39_50/_article/-char/ja/

• 根本 颯汰, 北田 俊輔, 彌冨 仁. “Majority or Minority: 固有表現抽出におけるデータの不均衡性に着目した損失関数の提案”.

Got Hosei University Research Grant for Doctoral Course Adopters in 2022 (480,000 JPY).

The following paper has been accepted to the IEEE Access.

• Shunsuke Kitada, Yuki Iwazaki, Riku Togashi, and Hitoshi Iyatomi. “DM$^2$S$^2$: Deep Multi-Modal Sequence Sets with Hierarchical Modality Attention”

The following paper has been accepted to the Springer Applied Intelligence.

• Shunsuke Kitada and Hitoshi Iyatomi. “Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training”

The following paper has been accepted to the IEEE HONET2022.

• Kazuya Ohata, Shunsuke Kitada and Hitoshi Iyatomi. “Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired”

• 北田 俊輔, 井上 直人, 大谷 まゆ, 彌冨 仁. “Document AI タスクに向けた大規模事前学習済みモデルを活用した Layout-aware Prompting”.
• 根本 颯汰, 北田 俊輔, 彌冨 仁. “固有表現認識タスクにおけるデータセットの偏りに着目した動的重み付け損失関数の提案”.

The following paper has been accepted to the ACM CIKM2022.

• Tsubasa Nakagawa, Shunsuke Kitada, and Hitoshi Iyatomi. “Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents”