Papers by Yusuke Kubota
Development of a General-Purpose Categorial Grammar Treebank (2020.lrec-1)
Copied to clipboard
| Challenge: | 'general-purpose' categorial grammar treebank is not tailored to specific variants of CG, but rather offers a theory-neutral linguistic resource that can be converted to different versions of 'type-logical grammar' . |
| Approach: | They propose a general-purpose categorial grammar treebank for Japanese that is not tailored to a specific variant of CG but rather offers a theory-neutral resource which can be converted to different versions of GC relatively easily. |
| Outcome: | The proposed treebank improves on the existing Japanese CG treebank on the treatment of certain linguistic phenomena (passives, causatives, and control/raising predicates). |
Cross-lingual and Word-Independent Methods for Quantifying Degree of Grammaticalization (2026.eacl-long)
Copied to clipboard
Ryo Nagata, Daichi Mochihashi, Misato Ido, Yusuke Kubota, Naoki Otani, Yoshifumi Kawasaki, Hiroya Takamura
| Challenge: | Existing methods for quantifying the degree of grammaticalization are language- and word-dependent . existing methods are language dependent and lack training data . |
| Approach: | They propose to use Positive-Unlabeled learning or Cross-Validation-like learning to quantify degree of grammaticalization. |
| Outcome: | The proposed method achieves high correlations to human judgments in English deverbal prepositions and Japanese nouns being grammaticalized. |