Skip to main content

Vocabulary of natural language processing

Search from vocabulary

Concept information

NLP resources and evaluation > measure > metric > Matthews correlation coefficient

Preferred term

Matthews correlation coefficient  

Definition

  • A measure of the quality of binary (two-class) classifications. (Wikipedia)

Broader concept

Synonym(s)

  • MCC
  • phi coefficient

Example

  • Additionally we incorporate the Matthews correlation coefficient (MCC) (Chicco and Jurman 2020) as an evaluation metric for sentence-level detection. (Jung, Eo & Lim, 2024)
  • Mathew's Correlation Coefficient (MCC) (Matthews 1975) is a suitable score for evaluating text classification tasks but its applicability to NER tasks is unclear. (Niklaus, Matoshi, Rani, Galassi, Stürmer & Chalkidis, 2023)
  • Matthews correlation coefficient (MCC) (Chicco and Jurman 2020) is used as a metric for evaluating QE model performance. (Eo, Park, Moon, Seo, Kim, Lee & Lim, 2022)
  • We incorporate Phi coefficient in our technique which is based on corpus-based term-to-term relatedness information and successfully handles the shortlength challenge of short texts. (Khan & Karim, 2012)
  • We then computed the Matthews correlation coefficient (MCC) between the controllability of the role label as measured by the SRL predictor with the gold controllability annotations for the subset of roles without annotation impossible. (Ross, Wu, Peng, Peters & Gardner, 2022)

In other languages

URI

http://data.loterre.fr/ark:/67375/8LP-ZP94H7LL-P

Download this concept:

RDF/XML TURTLE JSON-LD Last modified 5/2/24