Original title: The DURel Annotation Tool: Human and Computational Measurement of Semantic Proximity, Sense Clusters and Semantic Change
Authors: Dominik Schlechtweg, Shafqat Mumtaz Virk, Pauline Sander, Emma Sköldberg, Lukas Theuer Linke, Tuo Zhang, Nina Tahmasebi, Jonas Kuhn, Sabine Schulte im Walde
In the realm of word meanings, the DURel tool steps in as a powerful tool for understanding how words connect. It’s not just any tool—it’s an online platform where both people and computers team up to measure how closely related different word uses are. This tool is smart; it taps into advanced Word-in-Context models to do its magic. Humans make judgments on word connections, and the tool sorts these judgments into clusters using clever computer techniques. Then, it lays it all out visually for analysis. What’s neat is how easy it makes things. With simple tasks comparing word uses, it needs minimal setup. But it doesn’t stop there—it also checks how much people agree on these judgments to make sure they’re on the same page. Plus, it dishes out stats showing how word meanings vary or change over time. It’s like a detective unraveling the secrets behind how words evolve and connect.
Original article: https://arxiv.org/abs/2311.12664