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

• URL: http://arxiv.org/abs/2605.23710v1
• Date: Fri, 22 May 2026 14:55:54 GMT
• Title: A graph-based analysis of semantic types and coercion in contextualized word embeddings
• Abstract summary: This paper introduces a graph-based method to examine how lexical and contextual type information is reflected in word embeddings.<n>We select nouns from ten semantic types, annotate corpus instances for type matching, and construct graphs using BERT and sense-enhanced embeddings.<n>Results show that graphs constructed with sense-enhanced embeddings reflect semantic type information better.
• Score: 7.260528078468924
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Does Syntax Matter? A Graph-Augmented Variational Topic Model for Computational Social Sciences [51.56484100374058]
  This paper introduces the Structural Contextual Probabilistic Topic Model ( SCPTM), an architecture that incorporates syntactic dependency relations into topic inference.<n>We evaluate seven topic modeling techniques across four corpora differing in register and discourse structure.<n>Results show that SCPTM's neural architecture yields substantial gains in document-topic alignment over generative baselines.
  arXiv  Detail & Related papers  (2026-09-07T17:39:06Z)
• SMILE: A Composite Lexical-Semantic Metric for Question-Answering Evaluation [55.26111461168754]
  We introduce SMILE: Semantic Metric Integrating Lexical Exactness, a novel approach that combines sentence-level semantic understanding with keyword-level semantic understanding and easy keyword matching.<n>It is highly correlated with human judgments and computationally lightweight, bridging the gap between lexical and semantic evaluation.
  arXiv  Detail & Related papers  (2025-11-21T17:30:18Z)
• Using Synchronic Definitions and Semantic Relations to Classify Semantic Change Types [1.3436368800886478]
  We present a model that leverages information both from synchronic lexical relations and definitions of word meanings. Specifically, we use synset definitions and hierarchy information from WordNet and test it on a digitized version of Blank's (1997) dataset of semantic change types.
  arXiv  Detail & Related papers  (2024-06-05T16:52:21Z)
• An Investigation on Word Embedding Offset Clustering as Relationship Classification [0.0]
  This study is an investigation in an attempt to elicit a vector representation of relationships between pairs of word vectors. We use six pooling strategies to represent vector relationships. This work aims to provide directions for a word embedding based unsupervised method to identify the nature of a relationship represented by a pair of words.
  arXiv  Detail & Related papers  (2023-05-07T13:03:17Z)
• Prototype-based Embedding Network for Scene Graph Generation [105.97836135784794]
  Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. Due to the diverse visual appearance of numerous possible subject-object combinations, there is a large intra-class variation within each predicate category. Prototype-based Embedding Network (PE-Net) models entities/predicates with prototype-aligned compact and distinctive representations. PL is introduced to help PE-Net efficiently learn such entitypredicate matching, and Prototype Regularization (PR) is devised to relieve the ambiguous entity-predicate matching.
  arXiv  Detail & Related papers  (2023-03-13T13:30:59Z)
• Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification [68.06496970320595]
  Cross-domain sentiment classification (CDSC) aims to use the transferable semantics learned from the source domain to predict the sentiment of reviews in the unlabeled target domain. We present Graph Adaptive Semantic Transfer (GAST) model, an adaptive syntactic graph embedding method that is able to learn domain-invariant semantics from both word sequences and syntactic graphs.
  arXiv  Detail & Related papers  (2022-05-18T07:47:01Z)
• Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification [60.233529926965836]
  We propose a new method called SHINE, which is based on graph neural network (GNN) for short text classification. First, we model the short text dataset as a hierarchical heterogeneous graph consisting of word-level component graphs. Then, we dynamically learn a short document graph that facilitates effective label propagation among similar short texts.
  arXiv  Detail & Related papers  (2021-10-30T05:33:05Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Joint Graph Learning and Matching for Semantic Feature Correspondence [69.71998282148762]
  We propose a joint emphgraph learning and matching network, named GLAM, to explore reliable graph structures for boosting graph matching. The proposed method is evaluated on three popular visual matching benchmarks (Pascal VOC, Willow Object and SPair-71k) It outperforms previous state-of-the-art graph matching methods by significant margins on all benchmarks.
  arXiv  Detail & Related papers  (2021-09-01T08:24:02Z)
• Montague Grammar Induction [4.321645312120979]
  This framework provides the analyst fine-grained control over the assumptions that the induced grammar should conform to. We focus on the relationship between s(emantic)-selection and c(ategory)-selection, using as input a lexicon-scale acceptability judgment dataset.
  arXiv  Detail & Related papers  (2020-10-15T23:25:01Z)
• Embedding Words in Non-Vector Space with Unsupervised Graph Learning [33.51809615505692]
  We introduce GraphGlove: unsupervised graph word representations which are learned end-to-end. In our setting, each word is a node in a weighted graph and the distance between words is the shortest path distance between the corresponding nodes. We show that our graph-based representations substantially outperform vector-based methods on word similarity and analogy tasks.
  arXiv  Detail & Related papers  (2020-10-06T10:17:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.