Skip to main content

Vocabulary of natural language processing

Search from vocabulary

Concept information

Preferred term

semantic field  

Broader concept

Definitional context(s)

  • Semantic fields are sets of words tied together by "similarity" covering the most part of the lexical area of a specific domain. (Cavaglia, 1999)

Example

  • Ideally the semantic field can highlight the major visual concepts in images so that we can assign the correct semantic labels to the images. (Wang, Chua, Ngo & Wang, 2010)
  • In our approach we employ the Semantic Field to annotate the images which requires neither training data nor visual analysis and is running directly on the test data. (Wang, Chua, Ngo & Wang, 2010)
  • Semantic Fields are determined by a set of highly semantically associated terms with high tag co-occurrences in the image corpus and in different corpora and lexica such as WordNet and Wikipedia. (Wang, Chua, Ngo & Wang, 2010)
  • Semantic Fields consist of a selected subset of the tag list and the choice of these tags is based on their relevance to the contents of the targeted image with a specific sense. (Wang, Chua, Ngo & Wang, 2010)
  • Semantic fields that have been examined most extensively include color terms kinship terms spacial relations and motion verbs. (Ryzhova, Kyuseva & Paperno, 2016)

In other languages

URI

http://data.loterre.fr/ark:/67375/8LP-T9JF133X-P

Download this concept:

RDF/XML TURTLE JSON-LD Last modified 6/6/24