Automatic keyphrases extraction from document using backpropagation

Automatic keyphrase extraction from documents is a task with many applications in information retrieval and natural language processing. Previously, Several keyphrase extraction methods have been proposed based on different techniques. In this paper a keyphrase extraction approach based on backpropagation is proposed. In order to determine whether a phrase is a keyphrase or not, the following features of a phrase in a given document are adopted: its term frequency TF and inverted document frequency IDF, whether or not it appears in the title or headings (subheadings) of the given document, and its distribution in the paragraphs of the given document. The algorithm is evaluated by the standard information retrieval metrics of precision and recall and human assessment. Experiment results show that this approach is competitive with other known methods.