| 2022 | ACL | Word-level Perturbation Considering Word Length and Compositional Subwords. | Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki |
| 2021 | ACL | Joint Optimization of Tokenization and Downstream Model. | Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki |
| 2020 | COLING | How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text. | Chihiro Shibata, Kei Uchiumi, Daichi Mochihashi |
| 2020 | EMNLP | Optimizing Word Segmentation for Downstream Task. | Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki |
| 2015 | ACL | Inducing Word and Part-of-Speech with Pitman-Yor Hidden Semi-Markov Models. | Kei Uchiumi, Hiroshi Tsukahara, Daichi Mochihashi |
| 2015 | PACLIC | System Utterance Generation by Label Propagation over Association Graph of Words and Utterance Patterns for Open-Domain Dialogue Systems. | Hiroshi Tsukahara, Kei Uchiumi |
| 2011 | IJCNLP | Japanese Abbreviation Expansion with Query and Clickthrough Logs. | Kei Uchiumi, Mamoru Komachi, Keigo Machinaga, Toshiyuki Maezawa, Toshinori Satou, Yoshinori Kobayashi |
| 2009 | ACL | Learning Semantic Categories from Clickthrough Logs. | Mamoru Komachi, Shimpei Makimoto, Kei Uchiumi, Manabu Sassano |