Papers by Yusuke Kubota

2 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations