This paper presents a study on learning algorithms for keyphrase extraction. Keyphrases are phrases of two or more words that capture the main topics of a document. The authors propose two algorithms: C4.5, a decision tree induction algorithm, and GenEx, a hybrid genetic algorithm. The study evaluates the performance of these algorithms on five different document collections, with a total of 652 documents. The experiments show that GenEx outperforms C4.5 in generating keyphrases. Subjective human evaluation of the keyphrases generated by GenEx suggests that about 80% of the keyphrases are acceptable to human readers. The study also discusses related work in keyphrase extraction, information extraction, and index generation. The authors conclude that GenEx performs at a level suitable for many practical applications.This paper presents a study on learning algorithms for keyphrase extraction. Keyphrases are phrases of two or more words that capture the main topics of a document. The authors propose two algorithms: C4.5, a decision tree induction algorithm, and GenEx, a hybrid genetic algorithm. The study evaluates the performance of these algorithms on five different document collections, with a total of 652 documents. The experiments show that GenEx outperforms C4.5 in generating keyphrases. Subjective human evaluation of the keyphrases generated by GenEx suggests that about 80% of the keyphrases are acceptable to human readers. The study also discusses related work in keyphrase extraction, information extraction, and index generation. The authors conclude that GenEx performs at a level suitable for many practical applications.