AI RESEARCH
The LSCD Benchmark: a Testbed for Diachronic Word Meaning Tasks
arXiv CS.CL
•
ArXi:2404.00176v3 Announce Type: replace Lexical Semantic Change Detection (LSCD) is a complex, lemma-level task, which is usually operationalized based on two subsequently applied usage-level tasks: First, Word-in-Context (WiC) labels are derived for pairs of usages. Then, these labels are represented in a graph on which Word Sense Induction (WSI) is applied to derive sense clusters. Finally, LSCD labels are derived by comparing sense clusters over time. This modularity is reflected in most LSCD datasets and models.