Enriching Word Usage Graphs with Cluster Definitions

Mariia Fedorova, Andrey Kutuzov, Nikolay Arefyev, Dominik Schlechtweg
3/26/2024
cs.CL

No official code found. Best implementation: ltgoslo/wugs_with_definitions (2 stars, last commit 2024-09-19).

Abstract

We present a dataset of word usage graphs (WUGs), where the existing WUGs for multiple languages are enriched with cluster labels functioning as sense definitions. They are generated from scratch by fine-tuned encoder-decoder language models. The conducted human evaluation has shown that these definitions match the existing clusters in WUGs better than the definitions chosen from WordNet by two baseline systems. At the same time, the method is straightforward to use and easy to extend to new languages. The resulting enriched datasets can be extremely helpful for moving on to explainable semantic change modeling.

View on arXivView PDF

Code Implementations(1)

ltgoslo/wugs_with_definitionsCommunity100%

Methods that annotate word occurrences with glosses describing their meaning.

20Shell, PythonOct 4, 20232 years ago

Similar Papers

Graph-based Clustering for Detecting Semantic Change Across Time and Languages

85% match2024

Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis

79% match1 repo102023

Word-Centered Semantic Graphs for Interpretable Diachronic Sense Tracking

79% match2026

Explaining novel senses using definition generation with open language models

78% match2025

Multi-Sense Embeddings for Language Models and Knowledge Distillation

78% match2025

Definition generation for lexical semantic change detection

77% match1 repo42024

Cite this paper

@article{fedorova2024enriching,
  title  = {Enriching Word Usage Graphs with Cluster Definitions},
  author = {Mariia Fedorova and Andrey Kutuzov and Nikolay Arefyev and Dominik Schlechtweg},
  year   = {2024},
  eprint = {2403.18024},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.18024v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.18024.svg)](https://codeofpaper.com/paper/2403.18024)

Discussion