Anchovy uses the TypesTerms library for both monolingual term extraction and bilingual term extraction. In both cases, extraction is performed on XLIFF files.

TypesTerms identifies term candidates using the YAKE (Yet Another Keyword Extractor) algorithm, described in the paper YAKE! Keyword extraction from single documents using multiple local features by Ricardo Campos, Vítor Mangaravite, Arian Pasquali, Alípio Jorge, Célia Nunes and Adam Jatowt.

For monolingual extraction, a document in any of the supported formats is selected. Anchovy internally calls OpenXLIFF to convert the document to XLIFF before extracting the term candidates, so no manual conversion is required.

For bilingual extraction, a translated XLIFF 2.x file must be provided. Anchovy pairs the source and target term candidates found in it into a bilingual glossary.