Diachronic Usage Relatedness (DURel): A Framework for the Annotation of\n Lexical Semantic Change

2018/04/17 by Dominik Schlechtweg, Schlechtweg, Dominik, Sabine Schulte im Walde +3 · 1 citation
Computer Science · #Natural Language Processing Techniques #Authorship Attribution and Profiling #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1804.06517

Abstract

We propose a framework that extends synchronic polysemy annotation to\ndiachronic changes in lexical meaning, to counteract the lack of resources for\nevaluating computational models of lexical semantic change. Our framework\nexploits an intuitive notion of semantic relatedness, and distinguishes between\ninnovative and reductive meaning changes with high inter-annotator agreement.\nThe resulting test set for German comprises ratings from five annotators for\nthe relatedness of 1,320 use pairs across 22 target words.\n

Cited by

• XL-DURel: Finetuning Sentence Transformers for Ordinal Word-in-Context Classification

Related

• Survey of Computational Approaches to Lexical Semantic Change
• AXOLOTL'24 Shared Task on Multilingual Explainable Semantic Change Modeling
• A Wind of Change: Detecting and Evaluating Lexical Semantic Change\n across Times and Domains
• Using Synchronic Definitions and Semantic Relations to Classify Semantic Change Types
• Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices