Abstract
In recent years, language models (LMs) have become almost synonymous with NLP. Pre-trained to “read” a large text corpus, such models are useful as both a representation layer as well as a source of world knowledge. But how well do they represent MWEs? This talk will discuss various problems in representing MWEs, and the extent to which LMs address them: • Do LMs capture the implicit relationship between constituents in compositional MWEs (from baby oil through parsley cake to cheeseburger stabbing)? • Do LMs recognize when words are used nonliterally in non-compositional MWEs (e.g. do they know whether there are fleas in the flea market)? • Do LMs know idioms, and can they infer the meaning of new idioms from the context as humans often do?- Anthology ID:
- 2021.mwe-1.1
- Volume:
- Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venue:
- MWE
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1
- Language:
- URL:
- https://aclanthology.org/2021.mwe-1.1
- DOI:
- 10.18653/v1/2021.mwe-1.1
- Cite (ACL):
- Vered Shwartz. 2021. A Long Hard Look at MWEs in the Age of Language Models. In Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021), page 1, Online. Association for Computational Linguistics.
- Cite (Informal):
- A Long Hard Look at MWEs in the Age of Language Models (Shwartz, MWE 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.mwe-1.1.pdf