Skip to content

Getting Started

Welcome to the TermXtract tutorial series! Below are tutorials for each family of extraction methods:

  • TF-IDF Tutorial: Learn how to use the TF-IDF method for term extraction, on plain text and on a Teanga corpus.
  • Reference Corpus Tutorial: Find domain terms by comparing your documents with general-language text, using Weirdness, Domain Pertinence and Relevance.
  • Supervised Methods Tutorial: Train a term extractor from labelled examples with Roger or a transformer model.

Follow each tutorial to get started with term extraction in TermXtract.