A graph-based analysis of semantic types and coercion in contextualized word embeddings

2026-05-22 · Long Chen, Deniz Ekin Yavas arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.23710

Code (0)

등록된 구현이 없습니다.

Annotating Croatian Semantic Type Coercions in CROATPAS

2020-05-01 · LREC 2020 5 · Costanza Marini, Elisabetta Jezek

This short research paper presents the results of a corpus-based metonymy annotation exercise on a sample of 101 Croatian verb entries {--} corresponding to 457 patters and over 20,000 corpus lines {--} taken from CROATP…

Vocal Bursts Type Prediction

Contextualized language models for semantic change detection: lessons learned

2022-08-31 · Andrey Kutuzov, Erik Velldal, Lilja Øvrelid

We present a qualitative analysis of the (potentially erroneous) outputs of contextualized embedding-based methods for detecting diachronic semantic change. First, we introduce an ensemble method outperforming previously…

Change Detection

A Distributional Model of Affordances in Semantic Type Coercion

2019-05-01 · WS 2019 5 · Stephen McGregor, Elisabetta Jezek

We explore a novel application for interpreting semantic type coercions, motivated by insight into the role that perceptual affordances play in the selection of the semantic roles of artefactual nouns which are observed …

Vocal Bursts Type Prediction

A Geometric Method for Detecting Semantic Coercion

2017-01-01 · WS 2017 1 · Stephen McGregor, Elisabetta Jezek, Matthew Purver, Geraint Wiggins

Semantic Role Labeling for Knowledge Graph Extraction from Text

2018-11-04 · Mehwish Alam, Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero

This paper introduces TakeFive, a new semantic role labeling method that transforms a text into a frame-oriented knowledge graph. It performs dependency parsing, identifies the words that evoke lexical frames, locates th…

Dependency Parsing Semantic Role Labeling