A study of semantic projection from single word terms to multi-word terms in the environment domain - Archive ouverte HAL Access content directly
Conference Papers Year :

A study of semantic projection from single word terms to multi-word terms in the environment domain

Yizhe Wang
  • Function : Author
  • PersonId : 1041420
Nabil Hathout

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.
Fichier principal
Vignette du fichier
Computerm.pdf (115.16 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03478024 , version 1 (05-04-2022)

Identifiers

  • HAL Id : hal-03478024 , version 1

Cite

Yizhe Wang, Béatrice Daille, Nabil Hathout. A study of semantic projection from single word terms to multi-word terms in the environment domain. 6th International Workshop on Computational Terminology (COMPUTERM 2020), May 2020, Marseille, France. pp.ISBN 979-10-95546-57-3. ⟨hal-03478024⟩
42 View
6 Download

Share

Gmail Facebook Twitter LinkedIn More