Abstract
The semantic projection method is often used in terminology structuring to infer semantic relations between terms. Semantic projection relies upon the assumption of semantic compositionality: the relation that links simple term pairs remains valid in pairs of complex terms built from these simple terms. This paper proposes to investigate whether this assumption commonly adopted in natural language processing is actually valid. First, we describe the process of constructing a list of semantically linked multi-word terms (MWTs) related to the environmental field through the extraction of semantic variants. Second, we present our analysis of the results from the semantic projection. We find that contexts play an essential role in defining the relations between MWTs.- Anthology ID:
- 2020.computerm-1.7
- Volume:
- Proceedings of the 6th International Workshop on Computational Terminology
- Month:
- May
- Year:
- 2020
- Address:
- Marseille, France
- Venue:
- CompuTerm
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 50–54
- Language:
- English
- URL:
- https://aclanthology.org/2020.computerm-1.7
- DOI:
- Cite (ACL):
- Yizhe Wang, Beatrice Daille, and Nabil Hathout. 2020. A study of semantic projection from single word terms to multi-word terms in the environment domain. In Proceedings of the 6th International Workshop on Computational Terminology, pages 50–54, Marseille, France. European Language Resources Association.
- Cite (Informal):
- A study of semantic projection from single word terms to multi-word terms in the environment domain (Wang et al., CompuTerm 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.computerm-1.7.pdf