Supervised learning algorithms applied to terminology extraction

In this paper we present a new terminology extraction system based on supervised statistical learning algorithms, which are characterized by having a training phase with a controlled exposure to both positive and negative examples prior to the actual categorization. Contrary to the vast majority of the term extractors reported in the literature, our proposal is based on implicit knowledge rather than handcrafted explicit rules. Given a list of terms from some domain and language plus a general language reference corpus, we developed a methodology for terminology extraction and implemented it as a web application that is already available online. This tool is flexible enough to operate in different languages and domains and, as a sort of lifelong learning algorithm, it turns terminology extraction into a collaborative effort, where all users benefit from the training conducted by each individual.