Enriching Word Usage Graphs with Cluster Definitions
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 12 of its 25 references that are in the map. First posted on arXiv 26 Mar 2024.
Builds on
12 of 25 references.
References · 12
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
- 2020SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detectioncited by 105
- 2020Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoderscited by 61
- 2018Conditional Generators of Words Definitionscited by 35
- 2021DWUG: A large Resource of Diachronic Word Usage Graphs in Four Languagescited by 25
- 2022Contextualized language models for semantic change detection: lessons learnedcited by 20
- 2023Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysiscited by 19
- 2022Semeval-2022 Task 1: CODWOE -- Comparing Dictionaries and Word Embeddingscited by 18
- 2022NorDiaChange: Diachronic Semantic Change Dataset for Norwegiancited by 7
- 2022RuDSI: graph-based word sense induction dataset for Russiancited by 7
Built on by
Citing papers per year: 2024: 1.
1 paper.