Title :
Turkish keyphrase extraction using KEA
Author :
Pala, Nagehan ; Cicekli, Ilyas
Author_Institution :
Bilkent Univ., Ankara
Abstract :
Keyphrases provide semantic metadata to summarize and characterize documents. Unfortunately, there are many digital documents especially on the Internet that do not have a list of assigned keyphrases. Assigning keyphrases to these documents manually is a tedious process and requires knowledge of the subject. Automatic keyphrase extraction solves this problem. In this paper, we present implementation of keyphrase extraction algorithm (KEA) for Turkish as well as extending it with new features to improve its performance.
Keywords :
information retrieval; natural language processing; text analysis; Turkish keyphrase extraction; digital documents; document summarization; keyphrase extraction algorithm; semantic metadata; Artificial intelligence; Data mining; Frequency; Indexing; Internet; Machine learning; Machine learning algorithms; Supervised learning; Testing; Training data;
Conference_Titel :
Computer and information sciences, 2007. iscis 2007. 22nd international symposium on
Conference_Location :
Ankara
Print_ISBN :
978-1-4244-1363-8
Electronic_ISBN :
978-1-4244-1364-5
DOI :
10.1109/ISCIS.2007.4456860
