What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language
Abstract
Compositionality is a widely discussed property of natural languages, although its exact definition has been elusive. We focus on the proposal that compositionality can be assessed by measuring meaning-form correlation. We analyze meaning-form correlation on three sets of languages: (i) artificial toy languages tailored to be compositional, (ii) a set of English dictionary definitions, and (iii) a set of English sentences drawn from literature. We find that linguistic phenomena such as synonymy and ungrounded stop-words weigh on MFC measurements, and that straightforward methods to mitigate their effects have widely varying results depending on the dataset they are applied to. Data and code are made publicly available.- Anthology ID:
- 2020.coling-main.333
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 3737–3749
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.333
- DOI:
- 10.18653/v1/2020.coling-main.333
- Cite (ACL):
- Timothee Mickus, Timothée Bernard, and Denis Paperno. 2020. What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3737–3749, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language (Mickus et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.coling-main.333.pdf
- Data
- SICK