@inbook{7396bae9bbd547d785e1d107b2377f41,
title = "A comparative evaluation of term recognition algorithms",
abstract = "Automatic Term Recognition (ATR) is a fundamental processing step preceding more complex tasks such as semantic search and ontology learning. From a large number of methodologies available in the literature only a few are able to handle both single and multi-word terms. In this paper we present a comparison of five such algorithms and propose a combined approach using a voting mechanism. We evaluated the six approaches using two different corpora and show how the voting algorithm performs best on one corpus (a collection of texts from Wikipedia) and less well using the Genia corpus (a standard life science corpus). This indicates that choice and design of corpus has a major impact on the evaluation of term recognition algorithms. Our experiments also showed that single-word terms can be equally important and occupy a fairly large proportion in certain domains. As a result, algorithms that ignore single-word terms may cause problems to tasks built on top of ATR. Effective ATR systems also need to take into account both the unstructured text and the structured aspects and this means information extraction techniques need to be integrated into the term recognition process.",
keywords = "automatic term recognition, ATR, semantic search, ontology learning",
author = "Ziqi Zhang and Jos{\'e} Iria and Christopher Brewster and Fabio Ciravegna",
year = "2008",
month = may,
language = "English",
pages = "2108--2111",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC08)",
note = "6th International Conference on Language Resources and Evaluation, LREC 2008 ; Conference date: 01-05-2008",
}