Using machine learning to perform automatic term recognition
Jody Foo, Magnus Merkel · 2010
In this paper a machine learning approach is applied to Automatic Term Recognition (ATR). Similar approaches have been successfully used in Automatic Keyword Extraction (AKE). Using a dataset consisting of Swedish patent texts and validated terms belonging to these texts, unigrams and bigrams are extracted and annotated with linguistic and statistical feature values. Experiments using a varying ratio between positive and negative examples in the training data are conducted using the annotated n-grams. The results indicate that a machine learning approach is viable for ATR. Furthermore, a machine learning approach for bilingual ATR is discussed. Preliminary analysis however indicate that some modifications have to be made to apply the monolingual machine learning approach to a bilingual context. 1. Background Term extraction, or more specifically, Automatic Term Recognition (ATR) is a field in language technology that involves “extraction of technical terms from domain-specific language corpora. ” (Zhang et al., 2008). One area of application of ATR systems is the field of terminology where one task is to define concepts and decide which terms should