Automatic Sense Tagging Using Parallel Corpora.
Nancy Ide, Tomaž Erjavec, Dan Ioan Tufis · 2001
This article reports the results of an analysis of translation equivalents in six languages from different language families, extracted from an on-line parallel corpus of George Orwell's Nineteen Eighty-Four. The goal is to determine sense distinctions that can be used to automatically sense-tag the data. Our results show that sense distinctions derived from crosslingual information correspond to those made by human annotators, especially at the coarse-grained level.