Kazutoshi Shinoda

Can also be found in Google Scholar, dblp, and Semantic Scholar

Conference/Workshop Papers (Refereed)

  • Saki Mizuno, Nobukatsu Hojo, Kazutoshi Shinoda, Keita Suzuki, Mana Ihori, Hiroshi Sato, Tomohiro Tanaka, Naotaka Kawata, Satoshi Kobashikawa, Ryo Masumura: “Talking Face Generation for Impression Conversion Considering Speech Semantics.” In Proceedings of ICASSP, pages 8411–8415. Seoul, Korea. April, 2024.
  • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa: “Which Shortcut Solution Do Question Answering Models Prefer to Learn?” In Proceedings of the 37th AAAI conference on Artificial Intelligence (AAAI), pages 13564–13572. Washington, DC, USA. February, 2023. (acceptance rate = 19.6%, Oral)
  • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa: “Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering.” The Workshop on Knowledge Augmented Methods for NLP (KnowledgeNLP) at AAAI 2023. Washington, DC, USA. February, 2023.
  • Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo: “Improving the Robustness to Variations of Objects and Instructions with A Neuro-Symbolic Approach for Interactive Instruction Following.” In Proceedings of the 29th Internatinal Conference on Multimedia Modeling (MMM), pages 635–646. Bergen, Norway. January, 2023. (acceptance rate = 39.4%)
  • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa: “Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering.” In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP at EMNLP 2022, pages 418–425. Abu Dhabi, United Arab Emirates. December, 2022. (acceptance rate = 62.5%)
  • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa: “Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap.” In Proceedings of the 3rd Workshop on Machine Reading for Question Answering (MRQA) at EMNLP 2021, pages 63–72. Punta Cana, Dominican Republic. November 2021. (acceptance rate = 76%)
  • Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa: “Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation.” In Proceedings of the ACL-IJCNLP 2021 Student Research Workshop, pages 197–214. Online. August, 2021. (acceptance rate = 39%)
  • Kyosuke Nishida, Itsumi Saito, Kosuke Nishida, Kazutoshi Shinoda, Atsushi Otsuka, Hisako Asano, Junji Tomita: “Multi-style Generative Reading Comprehension.” In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), pages 2273–2284. Florence, Italy. July, 2019. (acceptance rate = 26%)
  • Kazutoshi Shinoda, Akiko Aizawa: “Query-focused Scientific Paper Summarization with Localized Sentence Representation.” In Proceedings of the 3rd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2018) at SIGIR 2018, pages 24–31. Ann Arbor, USA. July, 2018. (acceptance rate = 50%)
  • Hayato Hashimoto, Kazutoshi Shinoda, Hikaru Yokono, Akiko Aizawa: “Automatic Generation of Review Matrices as Multi-document Summarization of Scientific Papers.” In Proceedings of the 2nd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2017) at SIGIR 2017, pages 69–82. Tokyo, Japan. August, 2017. (acceptance rate = 50%)

Others (Unrefereed)

Domestic conferences, symposia, preprints, etc.

  • 篠田一聡, 菅原朔, 相澤彰子: “質問応答モデルはどのショートカットを優先して学習するか？” 言語処理学会第30回年次大会(NLP2024), 神戸, 兵庫, 2024.
  • 篠田一聡, 菅原朔, 相澤彰子: “抽出型質問応答における相対位置バイアスの除去.” 言語処理学会第28回年次大会(NLP2022), オンライン, 2022.
  • Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo: “Improving the Robustness to Variations of Objects and Instructions with A Neuro-Symbolic Approach for Interactive Instruction Following.” The 1st Workshop on Novel Ideas in Learning-to-Learn through Interaction (NILLI) at EMNLP 2021. Punta Cana, Dominican Republic. November, 2021. (non-archival)
  • 篠田一聡, 竹澤祐貴, 鈴木雅大, 岩澤有祐, 松尾豊: “Interactive Instruction FollowingのためのNeuro-Symbolic手法による多様な物体と言語指示への頑健性の向上.” 人工知能学会第35回全国大会(JSAI2021), オンライン, 2021.
  • 竹澤祐貴, 篠田一聡, 鈴木雅大, 岩澤有祐, 松尾豊: “Instruction Followingにおける構成的タスク表現の獲得.” 人工知能学会第35回全国大会(JSAI2021), オンライン, 2021.
  • 篠田一聡, 菅原朔, 相澤彰子: “変分質問回答ペア生成による質問応答モデルの汎化性能と頑健性の向上.” 言語処理学会第27回年次大会(NLP2021), オンライン, 2021.
  • Phuc Nguyen, Kazutoshi Shinoda, Taku Sakamoto, Diana Andreea Petrescu, Hung Nghiep Tran, Atsuhiro Takasu, Akiko Aizawa, Hideaki Takeda: “NII Table Linker at the NTCIR-15 Data Search Task: Re-ranking with Pre-trained Contextualized Embeddings, Data Content, Entity-centric, and Cluster-based Approaches.” In Proceedings of the 15th NTCIR Conference on Evaluation of Information Access Technologies, Tokyo, Japan, 2020. Presentation Award
  • 篠田一聡, 竹澤祐貴, 鈴木雅大, 岩澤有祐, 松尾豊: “Instruction Followingにおけるサブタスクへの分割と抽象化された行動の予測による長い行動系列への頑健性の向上.” 第16回 人工知能学会 汎用人工知能研究会(SIG-AGI), オンライン, 2020. 研究会優秀賞受賞
  • 篠田一聡, 相澤彰子: “深くて速い言語理解の実現に向けて.” 2019. NLP若手の会(YANS) 第14回シンポジウム.
  • 西田京介, 斉藤いつみ, 西田光甫, 篠田一聡, 大塚淳史, 浅野久子, 富田準二: “回答スタイルを制御可能な生成型機械読解.” 言語処理学会第25回年次大会(NLP2019), 名古屋大学(愛知), 2019. 優秀賞受賞
  • Hayato Hashimoto, Kazutoshi Shinoda, Hikaru Yokono, Akiko Aizawa: “Automatic Generation of Review Matrices as Multi-document Summarization of Scientific Papers.” Second International Workshop on SCIentific DOCument Analysis (SCIDOCA 2017), associated with JSAI International Symposia on AI 2017 (IsAI-2017). Tokyo Campus, Bunkyo School Building, University of Tsukuba, Tokyo, 2017.