A competition on word disambiguation

We invite participants to benchmark systems for word sense induction (WSI) across multiple languages. Unlike traditional approaches, this task evaluates WSI without relying on predefined sense inventories, offering a more theoretically plausible framework for understanding word meanings.

Participants will be provided with:

• A set of polysemous target headwords.
• Sentences containing these words in diverse contexts.

The goal is to cluster the sentences according to the sense in which the target word is used.

A different set of headwords and contexts will be provided for each of the following languages: English, Czech, German, Spanish, Estonian, Chinese

For each language, there will be approximately 25 headwords with 1500+ contexts each.