Papers by Yoshifumi Kawasaki

4 papers
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

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.

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