Logo Logo
Switch Language to German

Senel, Lütfi Kerem; Schick, Timo and Schütze, Hinrich (May 2022): CoDA21: Evaluating Language Understanding Capabilities of NLP Models With Context-Definition Alignment. 60th Annual Meeting of the Association for Computational Linguistics, Dublin, Ireland, May 2022. Muresan, Smaranda; Nakov, Preslav and Villavicencio, Aline (eds.) : In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Stroudsburg, PA: Association for Computational Linguistics. pp. 815-824 [PDF, 290kB]


Pretrained language models (PLMs) have achieved superhuman performance on many benchmarks, creating a need for harder tasks. We introduce CoDA21 (Context Definition Alignment), a challenging benchmark that measures natural language understanding (NLU) capabilities of PLMs: Given a definition and a context each for k words, but not the words themselves, the task is to align the k definitions with the k contexts. CoDA21 requires a deep understanding of contexts and definitions, including complex inference and world knowledge. We find that there is a large gap between human and PLM performance, suggesting that CoDA21 measures an aspect of NLU that is not sufficiently covered in existing benchmarks.

Actions (login required)

View Item View Item