CoDA21: Evaluating Language Understanding Capabilities of NLP Models With Context-Definition Alignment

Senel, Lütfi Kerem; Schick, Timo und Schütze, Hinrich (Mai 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 und Villavicencio, Aline (Hrsg.): In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Stroudsburg, PA: Association for Computational Linguistics. S. 815-824

Abstract

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.

• Dokumententyp: Konferenzbeitrag (Paper)
• EU Funded Grant Agreement Number: 740516
• EU-Projekte: Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement
• Fakultätsübergreifende Einrichtungen: Centrum für Informations- und Sprachverarbeitung (CIS)
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 000 Informatik, Wissen, Systeme ; 400 Sprache > 400 Sprache ; 400 Sprache > 410 Linguistik
• Ort: Stroudsburg, PA
• Sprache: Englisch