Shun Kiyono

メールアドレス:shun.kiyono [atat] sbintuitions.co.jp

Career

Education

Publications

Journal

  1. Shun Kiyono, Jun Suzuki, Tomoya Mizumoto, and Kentaro Inui. 2020. Massive Exploration of Pseudo Data for Grammatical Error Correction. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28:2134–2145.

International Conference

  1. Shun Kiyono, Sho Takase, Shengzhe Li, and Toshinori Sato. 2023. Bridging the Gap between Subword and Character Segmentation in Pretrained Language Models. In Ruslan Mitkov and Galia Angelova, editors, Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 568–577.
  2. Sho Takase, Shun Kiyono, Sosuke Kobayashi, and Jun Suzuki. 2023. B2T Connection: Serving Stability and Performance in Deep Transformers. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Association for Computational Linguistics: ACL 2023, pages 3078–3095. Association for Computational Linguistics.
  3. Sho Takase and Shun Kiyono. 2023. Lessons on Parameter Sharing across Layers in Transformers. In Nafise Sadat Moosavi, Iryna Gurevych, Yufang Hou, Gyuwan Kim, Young Jin Kim, Tal Schuster, and Ameeta Agrawal, editors, Proceedings of The Fourth Workshop on Simple and Efficient Natural Language Processing (SustaiNLP), pages 78–90. Association for Computational Linguistics.
  4. Makoto Morishita, Keito Kudo, Yui Oka, Katsuki Chousa, Shun Kiyono, Sho Takase, and Jun Suzuki. 2022. NT5 at WMT 2022 General Translation Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 318–325. Association for Computational Linguistics.
  5. Shun Kiyono, Sosuke Kobayashi, Jun Suzuki, and Kentaro Inui. 2021. SHAPE: Shifted Absolute Position Embedding for Transformers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3309–3321. November.
  6. Ryuto Konno, Shun Kiyono, Yuichiroh Matsubayashi, Hiroki Ouchi, and Kentaro Inui. 2021. Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3790–3806. November.
  7. Sho Takase and Shun Kiyono. 2021. Rethinking Perturbations in Encoder-Decoders for Fast Training. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2021), pages 5767–5780, OnlineJune. Association for Computational Linguistics.
  8. Shun Kiyono, Takumi Ito, Ryuto Konno, Makoto Morishita, and Jun Suzuki. 2020. Tohoku-AIP-NTT at WMT 2020 News Translation Task. In Proceedings of the Fifth Conference on Machine Translation (WMT2020), pages 144–154, OnlineNovember. Association for Computational Linguistics.
  9. Ryuto Konno, Yuichiroh Matsubayashi, Shun Kiyono, Hiroki Ouchi, Ryo Takahashi, and Kentaro Inui. 2020. An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution. In Proceedings of the 28th International Conference on Computational Linguistics (COLING2020), pages 4956–4968, Barcelona, Spain (Online)December. International Committee on Computational Linguistics.
  10. Masato Mita, Shun Kiyono, Masahiro Kaneko, Jun Suzuki, and Kentaro Inui. 2020. A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 267–280, OnlineNovember. Association for Computational Linguistics.
  11. Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki, and Kentaro Inui. 2020. Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction. In Proceedings of the 58th Conference of the Association for Computational Linguistics (ACL2020), pages 4248–4254. July.
  12. Hirofumi Inaguma, Shun Kiyono, Kevin Duh, Shigeki Karita, Nelson Enrique Yalta Soplin, Tomoki Hayashi, and Shinji Watanabe. 2020. ESPnet-ST: All-in-One Speech Translation Toolkit. In Proceedings of the 58th Conference of the Association for Computational Linguistics: System Demonstrations (ACL2020 Demo), pages 302–311. July.
  13. Shun Kiyono, Jun Suzuki, Masato Mita, Tomoya Mizumoto, and Kentaro Inui. 2019. An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction. In 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP2019), pages 1236–1242. November.
  14. Motoki Sato, Jun Suzuki, and Shun Kiyono. 2019. Effective Adversarial Regularization for Neural Machine Translation. In Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL2019), pages 204–210. July.
  15. Shun Kiyono, Jun Suzuki, and Kentaro Inui. 2019. Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework. In The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI2019), pages 4073–4081. January.
  16. Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, and Masaaki Nagata. 2018. Reducing Odd Generation from Neural Headline Generation. In 32nd Pacific Asia Conference on Language, Information and Computation (PACLIC 32), pages 289–303. December.
  17. Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, and Masaaki Nagata. 2018. Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models. In Analyzing and Interpreting Neural Networks for NLP (EMNLP2018 Workshop), pages 74–81. November.

Domestic Conference

  1. 清野 舜, 高瀬 翔, 李 聖哲, and 佐藤 敏紀. 2023. 入力の分割単位について頑健な言語モデルの構築. In 言語処理学会第29回年次大会予稿集, pages 789–794. March.
  2. 清野 舜, 小林 颯介, 鈴木 潤, and 乾 健太郎. 2022. シフト付き絶対位置埋め込み. In 言語処理学会第28回年次大会予稿集, pages 909–914. March.
  3. 高瀬 翔, 清野 舜, 小林 颯介, and 鈴木 潤. 2022. Transformerを多層にする際の勾配消失問題と解決法について. In 言語処理学会第28回年次大会予稿集, pages 173–178. March.
  4. 清野 舜, 小林 颯介, 鈴木 潤, and 乾 健太郎. 2021. 単一事例エキスパートの統合によるドメイン適応. In 言語処理学会第27回年次大会予稿集, pages 39–44. March.
  5. 松本 悠太, 清野 舜, and 乾 健太郎. 2021. 高再現率な文法誤り訂正システムの実現に向けて. In 言語処理学会第27回年次大会予稿集, pages 1475–1480. March.
  6. 高瀬 翔 and 清野 舜. 2021. エンコーダ・デコーダの学習に効果的な摂動の調査. In 言語処理学会第27回年次大会予稿集, pages 1391–1396. March.
  7. 今野 颯人, 松林 優一郎, 清野 舜, 大内 啓樹, and 乾 健太郎. 2021. 事前学習とfinetuningの類似性に基づくゼロ照応解析. In 言語処理学会第27回年次大会予稿集, pages 1718–1723. March.
  8. 清野 舜, 鈴木 潤, 三田 雅人, 水本 智也, and 乾 健太郎. 2020. 大規模疑似データを用いた高性能文法誤り訂正モデルの構築. In 言語処理学会第26回年次大会予稿集, pages 989–992. March.
  9. 今野 颯人, 松林 優一郎, 清野 舜, 大内 啓樹, 高橋 諒, and 乾 健太郎. 2020. マスク言語モデルを利用したデータ拡張に基づく日本語文内ゼロ照応解析. In 言語処理学会第26回年次大会予稿集, pages 1093–1096. March.
  10. 三田 雅人, 清野 舜, 金子 正弘, 鈴木 潤, and 乾 健太郎. 2020. 文法誤り訂正のための自己改良戦略に基づくノイズ除去. In 言語処理学会第26回年次大会予稿集, pages 993–996. March.
  11. 宮脇 峻平, 清野 舜, 松林 優一郎, 今野 颯人, 高橋 諒, 大内 啓樹, and 乾 健太郎. 2020. 反復改良法を用いた日本語述語項構造解析. In 言語処理学会第26回年次大会予稿集, pages 1097–1100. March.
  12. 今野 颯人, 松林 優一郎, 清野 舜, 高橋 諒, 大内 啓樹, and 乾 健太郎. 2019. BERTによる擬似訓練データ生成に基づく述語項構造解析. In 第14回NLP若手の会 シンポジウム. August.
  13. 宮脇 峻平, 加藤 拓真, 今野 颯人, 大内 啓樹, 清野 舜, 松林 優一郎, 高橋 諒, and 乾 健太郎. 2019. 日本語述語項構造のための自己回帰モデル. In 第14回NLP若手の会 シンポジウム. August.
  14. 藤井 諒, 清野 舜, 鈴木 潤, and 乾 健太郎. 2019. ニューラル機械翻訳における文脈情報の選択的利用. In 言語処理学会第25回年次大会予稿集, pages 1459–1462. March.
  15. 今野 颯人, 松林 優一郎, 大内 啓樹, 清野 舜, and 乾 健太郎. 2019. 前方文脈の埋め込みを利用した日本語述語項構造解析. In 言語処理学会第25回年次大会予稿集, pages 53–56. March.
  16. 北山 晃太郎, 清野 舜, 鈴木 潤, and 乾 健太郎. 2019. 画像言語同時埋め込みベクトル空間の構築に向けた埋め込み粒度の比較検討. In 言語処理学会第25回年次大会予稿集, pages 1419–1422. March.
  17. 清野 舜, 鈴木 潤, and 乾 健太郎. 2019. ExpertとImitatorの混合ネットワークによる大規模半教師あり学習. In 言語処理学会第25回年次大会予稿集, pages 1006–1009. March.
  18. 清野 舜, 高瀬 翔, 鈴木 潤, 岡崎 直観, 乾 健太郎, and 永田 昌晃. 2018. ニューラルヘッドライン生成における誤生成問題の改善. In 言語処理学会第24回年次大会予稿集, pages 1–4. March.
  19. 清野 舜, 田 然, 渡邉 研斗, 岡崎 直観, and 乾 健太郎. 2017. 談話関係認識のための時制情報の分析. In 言語処理学会第23回年次大会予稿集, pages 827–830. March.
  20. 清野 舜, 岡崎 直観, and 乾 健太郎. 2016. 質問応答タスクの設定と文章読解モデルの比較・検討. In 第11回NLP若手の会 シンポジウム. August.
  21. 清野 舜, 渡邉 研斗, 岡崎 直観, and 乾 健太郎. 2015. Bi-gram連接表と単語列変形規則に基づく回文自動生成. In 人工知能学会第29回全国大会. May.

Others

  1. 井尻善久, 牛久祥孝, 片岡裕雄, 藤吉弘亘, and 延原章平. 2024. コンピュータビジョン最前線 Summer 2024. edition, June.
  2. 清野 舜. 2022. 「SHAPE: Shifted Absolute Position Embedding for Transformers」の研究を通して. 自然言語処理, 29(1):248–252.
  3. 岡崎 直観, 清野 舜, 高橋 諒, and 横井 祥. 2020. 言語処理100本ノック. 自然言語処理, 27(3):2134–2145.
  4. Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, and Masaaki Nagata. 2017. Source-side Prediction for Neural Headline Generation. arXiv preprint arXiv:1712.08302, December.

Awards

Activities

Reviewer

Invited Talk

Tutorial

Others

その他