chapter  9
12 Pages

Term extraction

In Chapter 8, you learnt how you could search through a corpus to find information that was useful for producing a glossary. This chapter will introduce you to term extraction tools, which are also sometimes known as term recognition or term identification tools. These tools can help you to get a head start on glossary compilation by searching through corpora and extracting lists of potential terms that you might like to include in your glossary. One important thing to note is that although these tools are often referred to as automatic term extraction tools, this is actually a bit of a misnomer. Although the initial extraction attempt is performed by a computer, the resulting list of candidate terms contains just thatcandidates. As we will see, some of the candidates on the list may not be terms at all, whereas some actual terms in the corpus may be overlooked by the program and do not appear on the list. Therefore, the list of candidates must be verified by a human, and for this reason, the process is best described as being computer-aided or semi-automatic rather than fully automatic.