A key data preparation step in Text Mining, Term Extraction selects the terms, or collocation of words, attached to specific concepts. In this paper, the task of extracting relevant collocations is achieved through a supervised learning algorithm, exploiting a few collocations manually labelled as relevant/irrelevant. The candidate terms are described along 13 standard statistical criteria measures. From these examples, an evolutionary learning algorithm termed Roger, based on the optimization of the Area under the ROC curve criterion, extracts an order on the candidate terms. The robustness of the approach is demonstrated on two real-world domain applications, considering different domains (biology and human resources) and different languages (English and French).