ScholarGate
Assistent
Process / pipeline

Paraphrasedetektering — Identifikation af semantisk ækvivalens

Paraphrasedetektering er en opgave inden for naturlig sprogbehandling, der afgør, om to sætninger udtrykt med forskellige formuleringer bærer den samme betydning. Opgaven og dens benchmark-ressourcer blev etableret af Dolan og Brockett (2005) og ligger til grund for plagiatdetektering, spørgsmålsmatchning og datadublikering.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Dolan, W. B. & Brockett, C. (2005). Automatically Constructing a Corpus of Sentential Paraphrases. Proceedings of the Third International Workshop on Paraphrasing (IWP). link
  2. Wan, S., Dras, M., Dale, R. & Paris, C. (2006). Using Dependency-Based Features to Take the Para-farce Out of Paraphrase. Proceedings of the Australasian Language Technology Workshop (ALTA). link

Sådan citerer du denne side

ScholarGate. (2026, June 1). Paraphrase Detection. ScholarGate. https://scholargate.app/da/text-mining/paraphrase-detection

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Refereret af

ScholarGateParaphrase Detection (Paraphrase Detection). Hentet 2026-06-15 fra https://scholargate.app/da/text-mining/paraphrase-detection · Datasæt: https://doi.org/10.5281/zenodo.20539026