Ukyo Honda

I am a research scientist at CyberAgent AI Lab and also a visiting scientist at RIKEN Center for AIP.

My research interests include text generation and its evaluation. Currently, I am working on text generation with reinforcement learning and multimodal text generation. My dissertation was about enhancing scene coverage and informativeness of image captioning models.

Contact: honda_ukyo at cyberagent.co.jp
[Google Scholar] [Semantic Scholar] [GitHub] [Speaker Deck]

Publications

Refereed

• Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning
  Ukyo Honda, Taro Watanabe, and Yuji Matsumoto. WACV 2023.
  [arxiv][code]

• Explainable Natural Language Inference in the Legal Domain via Text Generation
  Jungmin Choi, Ukyo Honda, Taro Watanabe, and Kentaro Inui. Transactions of the Japanese Society for Artificial Intelligence 2023.

• Removing Partial Mismatches in Unsupervised Image Captioning
  Ukyo Honda, Atsushi Hashimoto, Taro Watanabe, and Yuji Matsumoto. Transactions of the Japanese Society for Artificial Intelligence 2022.

• Law Retrieval with Supervised Contrastive Learning using the Hierarchical Structure of Law
  Jungmin Choi, Ukyo Honda, Taro Watanabe, Kentaro Inui, and Hiroki Ouchi. PACLIC 2022.

• Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning
  Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe, and Yuji Matsumoto. EACL 2021.
  [arxiv][code]

• Characterization of Pulmonary Nodules in Computed Tomography Images Based on Pseudo-Labeling Using Radiology Reports
  Yohei Momoki, Akimichi Ichinose, Yutaro Shigeto, Ukyo Honda, Keigo Nakamura, and Yuji Matsumoto. IEEE Transactions on Circuits and Systems for Video Technology 2021.

• Pruning Basic Elements for Better Automatic Evaluation of Summaries
  Ukyo Honda, Tsutomu Hirao, and Masaaki Nagata. NAACL-HLT 2018.
  [code]

Non-Refereed

• 強化学習における画像キャプションの低識別性問題とLong-Tail分類手法を用いた対処
  本多右京, 渡辺太郎, 松本裕治. 言語処理学会第28回年次大会 2022.

• 法律の階層構造を利用した教師あり対照学習による法律検索
  チェ ジョンミン, 本多右京, 渡辺太郎, 大内啓樹. 第36回人工知能学会全国大会 2022.

• 画像と単語の不一致を考慮した疑似教師ありキャプション生成
  本多右京, 牛久祥孝, 橋本敦史, 渡辺太郎, 松本裕治. 言語処理学会第27回年次大会 2021.

• 冗長なNgram/Basic Elementsを除いた自動要約評価指標
  本多右京, 平尾努, 永田昌明. 言語処理学会第24回年次大会 2018.

Awards

• Best Paper Award / 最優秀賞
  Ukyo Honda, Taro Watanabe, and Yuji Matsumoto
  Annual Meeting of the Association for Natural Language Processing / 言語処理学会年次大会 (Mar. 2022)

• Outstanding Research Award / 優秀研究賞 (インタラクティブセッション発表部門)
  Jungmin Choi, Ukyo Honda, Taro Watanabe, Kentaro Inui, and Hiroki Ouchi
  Annual Conference of the Japanese Society for Artificial Intelligence / 人工知能学会全国大会 (Jun. 2022)

• Young Researcher Award / 若手奨励賞
  Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe, and Yuji Matsumoto
  Annual Meeting of the Association for Natural Language Processing / 言語処理学会年次大会 (Mar. 2021)

Education

• Mar. 2023: Ph.D. in Engineering at Nara Institute of Science and Technology

• Mar. 2019: M.S. in Engineering at Nara Institute of Science and Technology

• Sep. 2016: B.A. in Law at Keio University

Experience

• Sep. - Dec. 2019: Research Internship at OMRON SINIC X Corp.

• Aug. - Oct. 2018: Research Internship at OMRON SINIC X Corp.

• Sep. 2017: Research Internship at NTT Comunication Science Laboratories

• Sep. 2016 - Mar. 2017: Translation Checker at Honyaku Center Inc.

• Sep. 2015 - Jun. 2016: Exchange Student at University of California, Davis