Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.23710 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913156754833408 |
|---|---|
| author | Chen, Long Yavas, Deniz Ekin |
| author_facet | Chen, Long Yavas, Deniz Ekin |
| contents | Semantic type mismatch between a noun and its context is central to coercion phenomena. This paper introduces a graph-based method to examine how lexical and contextual type information is reflected in word embeddings. We select nouns from ten semantic types, annotate corpus instances for type matching (matching vs. coercion vs. other mismatch vs. unrestricted), and construct graphs using BERT and sense-enhanced embeddings. Two metrics -- Neighbor Type Probability (NTP) and Neighbor Type Entropy (NTE) -- are proposed to analyze neighborhood type distributions. Results show that graphs constructed with sense-enhanced embeddings reflect semantic type information better, and matching and mismatch sentences can be distinguished through the proposed metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23710 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A graph-based analysis of semantic types and coercion in contextualized word embeddings Chen, Long Yavas, Deniz Ekin Computation and Language Semantic type mismatch between a noun and its context is central to coercion phenomena. This paper introduces a graph-based method to examine how lexical and contextual type information is reflected in word embeddings. We select nouns from ten semantic types, annotate corpus instances for type matching (matching vs. coercion vs. other mismatch vs. unrestricted), and construct graphs using BERT and sense-enhanced embeddings. Two metrics -- Neighbor Type Probability (NTP) and Neighbor Type Entropy (NTE) -- are proposed to analyze neighborhood type distributions. Results show that graphs constructed with sense-enhanced embeddings reflect semantic type information better, and matching and mismatch sentences can be distinguished through the proposed metrics. |
| title | A graph-based analysis of semantic types and coercion in contextualized word embeddings |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.23710 |