Abstract
In the age of large transformer language models, linguistic evaluation play an important role in diagnosing models’ abilities and limitations on natural language understanding. However, current evaluation methods show some significant shortcomings. In particular, they do not provide insight into how well a language model captures distinct linguistic skills essential for language understanding and reasoning. Thus they fail to effectively map out the aspects of language understanding that remain challenging to existing models, which makes it hard to discover potential limitations in models and datasets. In this paper, we introduce Curriculum as a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. Curriculum contains a collection of datasets that covers 36 types of major linguistic phenomena and an evaluation procedure for diagnosing how well a language model captures reasoning skills for distinct types of linguistic phenomena. We show that this linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality. In addition, our experiments provide insight into the limitation of existing benchmark datasets and state-of-the-art models that may encourage future research on re-designing datasets, model architectures, and learning objectives.- Anthology ID:
- 2022.naacl-main.234
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3204–3219
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.234
- DOI:
- 10.18653/v1/2022.naacl-main.234
- Cite (ACL):
- Zeming Chen and Qiyue Gao. 2022. Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3204–3219, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding (Chen & Gao, NAACL 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.naacl-main.234.pdf
- Data
- ANLI, DROP, FEVER, GLUE, HELP, MultiNLI, SNLI