A corpus comparison approach for terminology extraction

Abstract

This article examines one of the possible approaches to identifying technical terms: a corpus comparison approach using the range and frequency of word forms. In order to identify terms using the corpus comparison approach, a ratio is used as a tool based on the comparative range and frequency of word forms between a technical corpus and a comparison corpus. A rating scale approach is used as the basis for evaluating the corpus comparison approach. The analysis shows that the corpus comparison approach works reasonably well with around 86% overlap with the results from the rating scale approach. It also shows that the corpus comparison approach using word types is a reasonably simple and practical way of identifying terms.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 136 citations exist upstream.