Papers by Yoshifumi Kawasaki
Variance Matters: Detecting Semantic Differences without Corpus/Word Alignment (2023.emnlp-main)
Copied to clipboard
| Challenge: | a new method for finding semantic differences in words appears in two corpora, but it requires a variance of word vectors . a word covers more meanings in a corpus, and its mean word vector becomes shorter . |
| Approach: | They propose a method to measure the coverage of meanings of a word in a corpus through the norm of its mean word vector. |
| Outcome: | The proposed methods rival the best-performing system in the SemEval-2020 Task 1 . they are robust for the skew in corpus sizes and capable of detecting infrequent words . |
Revisiting Statistical Laws of Semantic Shift in Romance Cognates (2022.coling-1)
Copied to clipboard
| Challenge: | Despite their shared etymology, some cognate pairs have experienced semantic shift. |
| Approach: | They examine the relationship between lexical semantic shift and six intra-linguistic variables, such as frequency and polysemy, and examine the effect of morphologically complex etyma on semantic shift. |
| Outcome: | The results show that frequency and polysemy have positive effects on semantic shift and that morphologically complex etyma are more resistant to it. |
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. |
A Computational Approach to Quantifying Grammaticization of English Deverbal Prepositions (2024.lrec-main)
Copied to clipboard
| Challenge: | Linguistic studies have revealed important aspects of grammaticization of deverbal prepositions. |
| Approach: | They propose a computational approach to measure the degree of grammaticization of deverbal prepositions based on corpus data. |
| Outcome: | The proposed method correlates well with human judgements and supports previous findings in linguistics. |