Publications

Preprints

1. LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs, arXiv:2407.03963. [paper]
2. Jungdae Lee, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo, Nakamasa Inoue, CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information, arXiv:2406.14240. [paper]
3. Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, Shinsuke Mori, Text-driven Affordance Learning from Egocentric Vision, arXiv:2404.02523. [paper]
4. Koki Maeda, Shuhei Kurita, Taiki Miyanishi, Naoaki Okazaki, Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction, arXiv:2402.17969. [paper]

Journals

5. Kouta Nakayama, Shuhei Kurita, Yukino Baba and Satoshi Sekine, “Wikipedia Link Extension and Expected Entity Rate Estimation for Training Named Entity Recognizer” (in Japanese), Natural Language Processing (in Japan), Vol.XX, No.X, p.XXXX-XXXX, (2024.9).
6. Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Shinsuke Mori, “Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows” (in Japanese), Natural Language Processing (in Japan), Vol.30, No.3, p.1042-1060, (2023.9).
7. Ryota Kobayashi, Shuhei Kurita, Anno Kurth, Katsunori Kitano, Kenji Mizuseki, Markus Diesmann, Barry J. Richmond & Shigeru Shinomoto, “Reconstructing neuronal circuitry from parallel spike trains,” Nature Communications, volume 10, Article number: 4468 (2019). [paper].
   My contribution: Large-scale biological neural network simulation.
8. Shuhei Kurita, Daisuke Kawahara and Sadao Kurohashi, “Neural Network-based Chinese Joint Syntactic Analysis” (in Japanese), Natural Language Processing (in Japan), Vol.26, No.1, p.231-258, (2019.3).

Proceedings

9. Mahiro Ukai, Shuhei Kurita, Atsushi Hashimoto, Yoshitaka Ushiku and Nakamasa Inoue, “AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering,” Proceedings of the 32th ACM International Conference on Multimedia (ACMMM2024), 2024. [arXiv]
10. Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto and Motoaki Kawanabe, “Answerability Fields: Answerable Location Estimation via Diffusion Models,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2024), 2024. [arXiv]
11. Koya Sakamoto, Daichi Azuma, Taiki Miyanishi, Shuhei Kurita and Motoaki Kawanabe, “Map-based Modular Approach for Zero-shot Embodied Question Answering,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2024), 2024. [arXiv]
12. Hao Wang, Shuhei Kurita, Shuichiro Shimizu, Daisuke Kawahara, SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition, 3rd Workshop on Advances in Language and Vision Research (ALVR) in ACL2024. [paper]
13. Rintaro Enomoto, Arseny Tolmachev, Takuro Niitsuma, Shuhei Kurita, and Daisuke Kawahara, “Investigating Web Corpus Filtering Methods for Language Model Development in Japanese.” In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 154–160, Mexico City, 2024. [paper]
14. Eri Onami, Shuhei Kurita, Taiki Miyanishi, and Taro Watanabe, “JDocQA: Japanese Document Question Answering Dataset for Generative Language Models,” In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9503–9514, Torino, 2024. [paper] [code]
15. Chieko Nishimura, Shuhei Kurita, and Yohei Seki, “Text360Nav: 360-Degree Image Captioning Dataset for Urban Pedestrians Navigation,” In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15783–15788, Torino, 2024. [paper]
16. Taiki Miyanishi, Daichi Azuma, Shuhei Kurita and Motoaki Kawanabe, “Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans,” International Conference on 3D Vision 2024 (3DV2024), 2024. [paper]
17. Taiki Miyanishi, Fumiya Kitamori, Shuhei Kurita, Jungdae Lee, Motoaki Kawanabe and Nakamasa Inoue, “CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data,” NeurIPS2023 Datasets and Benchmarks track, New Orleans, Dec. 2023. [paper] [code]
18. Koki Maeda, Shuhei Kurita, Taiki Miyanishi, and Naoaki Okazaki. “Query-based Image Captioning from Multi-context 360cdegree Images,” In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6940–6954, Singapore, 2023. [paper]
19. Shunya Kato, Shuhei Kurita, Chenhui Chu, and Sadao Kurohashi. “ARKitSceneRefer: Text-based Localization of Small Objects in Diverse Real-World 3D Indoor Scenes,” In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 784–799, Singapore, 2023. [paper] [code]
20. Yutaka Nakamura, Shuhei Kurita, and Koichiro Yoshino. “Language and Robotics: Toward Building Robots Coexisting with Human Society Using Language Interface,” In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Tutorial Abstract (AACL-IJCNLP Tutorial), pages 1–7, Bali, 2023. [paper]
21. Shuhei Kurita, Naoki Katsura and Eri Onami, “RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D,” IEEE/CVF International Conference on Computer Vision Workshop on Language for 3D Scenes, Paris, 2023.
22. Shuhei Kurita, Naoki Katsura and Eri Onami, “RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D,” Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV2023), pages 15214-15224, 2023. [arXiv] [code]
23. Shuhei Kurita, Hiroki Ouchi, Kentaro Inui, and Satoshi Sekine, “Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling,” In Proceedings of the 29th International Conference on Computational Linguistics, pages 5383–5397, Gyeongju, Republic of Korea, 2022. [paper]
24. Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku, and Shinsuke Mori, “Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows,” In Proceedings of the 29th International Conference on Computational Linguistics, pages 3570–3577, Gyeongju, Republic of Korea, 2022. [paper].
25. Daichi Azuma(*), Taiki Miyanishi(*), Shuhei Kurita(*) and Motoaki Kawanabe, “ScanQA: 3D Question Answering for Spatial Scene Understanding,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2022), pages 19129-19139, New Orleans, 2022. (*): Equally contributed. [paper] [arXiv] [code]
26. Kouta Nakayama, Shuhei Kurita, Akio Kobayashi, Yukino Baba, and Satoshi Sekine, “Co-Teaching Student-Model through Submission Results of Shared Task,” In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4525–4535, Punta Cana, 2021. [paper]
27. Shuhei Kurita and Kyunghyun Cho, “Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes’ Rule,” Ninth International Conference on Learning Representations (ICLR2021), Online, May 2021. [arXiv], [paper] [github], [OpenReview].
28. Shuhei Kurita and Kyunghyun Cho, “Toward Understanding Language-Grounded Agents in Vision-and-Language Navigation,” ICML 2020 Workshop on Learning in Artificial Open Worlds (ICML LAOW2020 Workshop), Online, July 2020. [link].
29. Shuhei Kurita and Anders Søgaard, “Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies,” In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, ACL2019, pages 2420–2430, Florence, Italy, 2019. [paper] [github] [paper].
30. Kobayashi R, Kurita S, Kitano K, Mizuseki K, Richmond B.J, Shinomoto S, “A method for estimating synaptic connections from parallel spike trains,” The 5th International Conference on Mathematical NeuroScience (ICMNS2019), Copenhagen, Denmark, June 2019.
31. Ryota Kobayashi, Shuhei Kurita, Katsunori Kitano, Kenji Mizuseki, Barry J. Richmond, Shigeru Shinomoto, “Estimation of synaptic connections from parallel spike trains,” The 13th international workshop of neural coding (NC2018), Torino, Italy, Sep. 2018.
32. Shuhei Kurita, Daisuke Kawahara, and Sadao Kurohashi. “Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis,” In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL2018, pages 474–484, Melbourne, 2018. [paper].
33. Shuhei Kurita, Daisuke Kawahara, and Sadao Kurohashi, “Neural Joint Model for Transition-based Chinese Syntactic Analysis,” In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL2017, pages 1204–1214, Vancouver, 2017. [paper].
    Selected as Out-standing Paper! (2% of submissions)
34. Ryota Kobayashi, Shuhei Kurita, Yuzuru Yamanaka, Katsunori Kitano and Shigeru Shinomoto, “Testing statistical significance of synaptic connectivity,” The 12th international workshop of neural coding, (NC2016), Cologne, Federal Republic of Germany, Sep. 2016.

Local Conferences

1. 鈴木雄太, 栗田修平, “論文の自動スクリーニングのための大規模言語モデルの応用”,第85回応用物理学会秋季学術講演会, 新潟, 2024.9.16-20, 2024.
2. 入澤優太, 伊東聖矢, 栗田修平, 赤坂亮太, 大西正輝, 大原剛三, 櫻田健, “LPT Dataset: 画像プライバシー認識を目的とした大規模言語モデルによるプライバシーテキストデータセットの構築” , MIRU2024, 熊本, 2024.8.6-9.
3. 東大地, 宮西大樹, 栗田修平, 坂本滉也, 川鍋一晃, “実世界質問応答のための拡散モデルを用いた回答可能位置の予測” , MIRU2024, 熊本, 2024.8.6-9.
4. 西村千恵子, 栗田修平, 関洋平，”都市環境における歩行者支援のための画像説明文生成用データセットの作成”，言語処理学会第30回年次大会, 神戸, 2024.3.11-15.
5. 大南英理, 栗田修平, 宮西大樹, 渡辺太郎，”JDocQA: 図表を含む日本語文書質問応答データセットによる大規模言語モデルチューニング”，言語処理学会第30回年次大会, 神戸, 2024.3.11-15.
6. 王昊, 栗田修平, 清水周一郎, 河原大輔，”SlideAVSR: 視聴覚音声認識のための論文解説動画データセット”，言語処理学会第30回年次大会, 神戸, 2024.3.11-15.
7. Arseny Tolmachev, Masayoshi Hayashi, Takuro Niitsuma, Rintaro Enomoto, Hao Wang, Shuhei Kurita, Daisuke Kawahara, Kazuma Takaoka, Yoshitaka Uchida，”Uzushio: A Distributed Huge Corpus Processor for the LLM Era”，言語処理学会第30回年次大会, 神戸, 2024.3.11-15.
8. 前田航希, 栗田修平, 宮西大樹, 岡崎直観，”視覚的文脈を利用した視覚言語モデルによる画像キャプション生成自動評価手法”，言語処理学会第30回年次大会, 神戸, 2024.3.11-15.
9. 吉田智哉, 栗田修平, 西村太一, 森信介，”一人称視点に基づくテキスト駆動型アフォーダンス及び軌跡の学習”，言語処理学会第30回年次大会, 神戸, 2024.3.11-15.
10. 榎本倫太郎, Arseny Tolmachev, 新妻巧朗, 栗田修平, 河原大輔，”大規模言語モデル開発における日本語 Web 文書のフィルタリング手法の検証”，言語処理学会第30回年次大会, 神戸, 2024.3.11-15.
11. 宮西大樹, 東大地, 栗田修平, 川鍋一晃，”異なるRGB-Dスキャンを用いたデータセット横断3D言語接地”，2023年度 人工知能学会全国大会（第37回）, 熊本, 2023.6.6-9．
12. 加藤駿弥, 栗田修平, Chenhui Chu, 黒橋禎夫，”ARKitSceneRefer: 3D屋内シーンでの参照表現による小物の位置特定”，言語処理学会第29回年次大会, 沖縄, 2023.3.13-17.
13. 前田航希, 栗田修平, 宮西大樹，”QuIC-360◦: 360◦ 画像に対するクエリ指向画像説明文生成のためのデータセット構築”，言語処理学会第29回年次大会, 沖縄, 2023.3.13-17.
14. 桂尚輝, 栗田修平, ”テキスト条件付き物体検出器と参照表現理解への応用”，第25回 画像の認識・理解シンポジウム(MIRU2022), 姫路, 2022.7.25-28.
15. 白井圭佑, 橋本敦史, 牛久祥孝, 栗田修平, 亀甲博貴, 森信介，”レシピ分野における動作対象の状態変化を考慮したデータセットの構築と検索モデルの提案”，言語処理学会第28回年次大会, オンライン, 2022.3.14-18.
16. 中山功太, 栗田修平, 小林暁雄, 馬場雪乃, 関根聡，”共有タスクへの結果提出を通した生徒モデルの共同教育手法”，言語処理学会第28回年次大会, オンライン, 2022.3.14-18.
17. 栗田修平, Kyunghyun Cho，”視覚と言語によるナビゲーション課題への言語に対応付けられた生成的な方策”，言語処理学会第27回年次大会, オンライン, 2021.3.15-19.
18. 中山功太, 栗田修平, 馬場雪乃, 関根聡，”能動的サンプリングを用いたリソース構築共有タスクにおける予測対象データ削減”，言語処理学会第27回年次大会, オンライン, 2021.3.15-19.
19. 中山功太, 栗田修平, 小林暁雄, 関根聡，”Pre-Distillation Ensemble:リソース構築タスクのためのアンサンブル手法”，言語処理学会第26回年次大会, オンライン, 2020.3.16-19.
20. Kobayashi R., Kurita S., Kitano K., Mizuseki K., Richmond B.J., and Shinomoto S., ”多細胞スパイクデータからシナプス結合を推定する技術の開発”，Neuro 2019, 新潟, 2019.7.
21. 栗田修平, Anders Søgaard，”深層強化学習を用いた意味依存構造解析は自発的に平易優先戦略を学習する”，言語処理学会第25回年次大会, 名古屋, 2019.3.11-15.
22. Ryota Kobayashi, Shuhei Kurita, Katsunori Kitano, Kenji Mizuseki, Barry J. Richmond and Shigeru Shinomoto，”Estimating synaptic connections from parallel spike trains”, 28th Annual Conference of Japanese Neural Network Society, Oral Session, Japan, Oct. 2018.
23. 栗田修平, 河原大輔, 黒橋禎夫，”ニューラルネットワークに基づく単語分割・品詞付与・構文解析の統合解析”，言語処理学会第23回年次大会, つくば, 2017.3.13-17.
24. 栗田修平, 小林亮太, 北野勝則, 篠本滋，”神経回路シミュレーションデータを用いた結合推定”，日本物理学会第69回年次大会, 27pAJ-13, 神奈川, 2014.3.
25. Shuhei Kurita, Yuzuru Yamanaka, Ryota Kobayashi, Katsunori Kitano and Shigeru Shinomoto，”Minimal time length of spike trains for the inference of connectivity”，24th Annual Conference of Japanese Neural Network Society, Oral and Poster Session 2 P2-08, Hakodate, Japan, Aug. 2014.

Invited Talks

1. テキストからの実世界理解に向けて
   第26回情報論的学習理論ワークショップ (2023 Oct. 29).
   栗田修平
2. 実世界を認識して動作するための言語理解技術
   NLP若手の会 (YANS) 第18回シンポジウム 招待セッション (2023 Aug 31). link
   栗田修平
3. 自然言語処理に用いられる深層学習 - 基礎から大規模言語モデルと応用までを解説 -
   ロボット工学セミナー (2023 June 9). link
   栗田修平
4. 実世界を認識して動作するための言語理解技術
   データ工学ロボティクスとNEDO特別講座共催講演会 (2023 Mar. 29). link
   栗田修平
5. ScanQA: 3D Question Answering for Spatial Scene Understanding
   MIRU2022 (2022 July 27).
   Daichi Azuma(*), Taiki Miyanishi(*), Shuhei Kurita(*) and Motoaki Kawanabe
   (*): equally contributed
6. 文解析における既存データセットの制約とそれを超える解析手法
   名古屋地区NLPセミナー(2019 May).
   栗田修平
7. 自然言語処理の既存データセットの制約を超えた文の解析手法
   理化学研究所AIP (2019 Feb.).
   栗田修平
8. Neural Joint Model for Transition-based Chinese Syntactic Analysis,
   Google NLP Summit, Zurich, Switzerland (2017 Oct.).
   Shuhei Kurita

Talks

1. 実世界にグラウンドされた自然言語理解のこれまでとこれから
   第7回Language and Robotics研究会 link slide
   栗田修平