Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912404667891712 |
|---|---|
| author | Kishino, Ryo Yamagiwa, Hiroaki Nagata, Ryo Yokoi, Sho Shimodaira, Hidetoshi |
| author_facet | Kishino, Ryo Yamagiwa, Hiroaki Nagata, Ryo Yokoi, Sho Shimodaira, Hidetoshi |
| contents | Lexical semantic change detection aims to identify shifts in word meanings over time. While existing methods using embeddings from a diachronic corpus pair estimate the degree of change for target words, they offer limited insight into changes at the level of individual usage instances. To address this, we apply Unbalanced Optimal Transport (UOT) to sets of contextualized word embeddings, capturing semantic change through the excess and deficit in the alignment between usage instances. In particular, we propose Sense Usage Shift (SUS), a measure that quantifies changes in the usage frequency of a word sense at each usage instance. By leveraging SUS, we demonstrate that several challenges in semantic change detection can be addressed in a unified manner, including quantifying instance-level semantic change and word-level tasks such as measuring the magnitude of semantic change and the broadening or narrowing of meaning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12569 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport Kishino, Ryo Yamagiwa, Hiroaki Nagata, Ryo Yokoi, Sho Shimodaira, Hidetoshi Computation and Language Lexical semantic change detection aims to identify shifts in word meanings over time. While existing methods using embeddings from a diachronic corpus pair estimate the degree of change for target words, they offer limited insight into changes at the level of individual usage instances. To address this, we apply Unbalanced Optimal Transport (UOT) to sets of contextualized word embeddings, capturing semantic change through the excess and deficit in the alignment between usage instances. In particular, we propose Sense Usage Shift (SUS), a measure that quantifies changes in the usage frequency of a word sense at each usage instance. By leveraging SUS, we demonstrate that several challenges in semantic change detection can be addressed in a unified manner, including quantifying instance-level semantic change and word-level tasks such as measuring the magnitude of semantic change and the broadening or narrowing of meaning. |
| title | Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.12569 |