Abstract
Logical approaches to representing language have developed and evaluated computational models of quantifier words since the 19th century, but today's NLU models still struggle to capture their semantics. We rely on Generalized Quantifier Theory for language-independent representations of the semantics of quantifier words, to quantify their contribution to the errors of NLU models. We find that quantifiers are pervasive in NLU benchmarks, and their occurrence at test time is associated with performance drops. Multilingual models also exhibit unsatisfying quantifier reasoning abilities, but not necessarily worse for non-English languages. To facilitate directly-targeted probing, we present an adversarial generalized quantifier NLI task (GQNLI) and show that pre-trained language models have a clear lack of robustness in generalized quantifier reasoning.
Originalsprog | Engelsk |
---|---|
Titel | NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies, Proceedings of the Conference |
Forlag | Association for Computational Linguistics (ACL) |
Publikationsdato | 2022 |
Sider | 4875-4893 |
ISBN (Elektronisk) | 9781955917711 |
DOI | |
Status | Udgivet - 2022 |
Begivenhed | 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 - Seattle, USA Varighed: 10 jul. 2022 → 15 jul. 2022 |
Konference
Konference | 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 |
---|---|
Land/Område | USA |
By | Seattle |
Periode | 10/07/2022 → 15/07/2022 |
Sponsor | Amazon, Bloomberg, et al., Google Research, LIVE PERSON, Meta |
Bibliografisk note
Funding Information:We would like to thank Miryam de Lhoneux, Con-stanza Fierro, Desmond Elliott and the anonymous reviewers for their valuable feedback.
Publisher Copyright:
© 2022 Association for Computational Linguistics.