What Can Diachronic Contexts and Topics Tell Us about the Present-Day Compositionality of English Noun Compounds?
Samin Mahdizadeh Sani, Malak Rassem, Chris Jenkins, Filip Miletić, Sabine Schulte im Walde
Abstract
Predicting the compositionality of noun compounds such as climate change and tennis elbow is a vital component in natural language understanding. While most previous computational methods that automatically determine the semantic relatedness between compounds and their constituents have applied a synchronic perspective, the current study investigates what diachronic changes in contexts and semantic topics of compounds and constituents reveal about the compounds’ present-day degrees of compositionality. We define a binary classification task that utilizes two diachronic vector spaces based on contextual co-occurrences and semantic topics, and demonstrate that diachronic changes in cosine similarities – measured over context or topic distributions – uncover patterns that distinguish between compounds with low and high present-day compositionality. Despite fewer dimensions in the topic models, the topic space performs on par with the co-occurrence space and captures rather similar information. Temporal similarities between compounds and modifiers as well as between compounds and their prepositional paraphrases predict the compounds’ present-day compositionality with accuracy >0.7.- Anthology ID:
- 2024.lrec-main.1517
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 17449–17458
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1517
- DOI:
- Cite (ACL):
- Samin Mahdizadeh Sani, Malak Rassem, Chris Jenkins, Filip Miletić, and Sabine Schulte im Walde. 2024. What Can Diachronic Contexts and Topics Tell Us about the Present-Day Compositionality of English Noun Compounds?. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17449–17458, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- What Can Diachronic Contexts and Topics Tell Us about the Present-Day Compositionality of English Noun Compounds? (Mahdizadeh Sani et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1517.pdf