EUVIMEDEUVIMED entdecken
Crossref

Domain embeddings for generating complex descriptions of concepts in Italian language

Alessandro Maisto

Cognitive Processing · 2025

DOI: 10.1007/s10339-024-01234-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cognitive Processing, 2025. Verfasst von Alessandro Maisto. Beteiligte Einrichtung: Department of Politics and Communication Science, University of Salerno, via Giovanni Paolo II, 132, 84084, Fisciano, SA, Italy. amaisto@unisa.it. Hauptthemen laut MEDLINE: Semantics, Language, Concept Formation, Linguistics. Die Arbeit nennt 80 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this work, we propose a Distributional Semantic resource enriched with linguistic and lexical information extracted from electronic dictionaries. This resource is designed to bridge the gap between the continuous semantic values represented by distributional vectors and the discrete descriptions provided by general semantics theory. Recently, many researchers have focused on the connection between embeddings and a comprehensive theory of semantics and meaning. This often involves translating the representation of word meanings in Distributional Models into a set of discrete, manually constructed properties, such as semantic primitives or features, using neural decoding techniques. Our approach introduces an alternative strategy based on linguistic data. We have developed a collection of domain-specific co-occurrence matrices derived from two sources: a list of Italian nouns classified into four semantic traits and 20 concrete noun sub-categories and Italian verbs classified by their semantic classes. In these matrices, the co-occurrence values for each word are calculated exclusively with a defined set of words relevant to a particular lexical domain. The resource includes 21 domain-specific matrices, one comprehensive matrix, and a Graphical User Interface. Our model facilitates the generation of reasoned semantic descriptions of concepts by selecting matrices directly associated with concrete conceptual knowledge, such as a matrix based on location nouns and the concept of animal habitats. We assessed the utility of the resource through two experiments, achieving promising outcomes in both the automatic classification of animal nouns and the extraction of animal features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SemanticsLanguageConcept FormationLinguisticsHumansItaly

Stichwörter der Autor:innen

Distributional semanticsElectronic resourceFeature semanticsInterpretability of embeddings

Autor:innen und Institutionen

  • Department of Politics and Communication Science, University of Salerno, via Giovanni Paolo II, 132, 84084, Fisciano, SA, Italy. amaisto@unisa.it.

Zitieren

APA

Maisto, A. (2025). Domain embeddings for generating complex descriptions of concepts in Italian language. Cognitive Processing. https://doi.org/10.1007/s10339-024-01234-9

Vancouver

Maisto A. Domain embeddings for generating complex descriptions of concepts in Italian language. Cognitive Processing. 2025. doi:10.1007/s10339-024-01234-9

BibTeX
@article{Maisto2025,
  author = {Maisto, Alessandro},
  title = {Domain embeddings for generating complex descriptions of concepts in Italian language},
  journal = {Cognitive Processing},
  year = {2025},
  doi = {10.1007/s10339-024-01234-9}
}
Kostenlos starten →