Browsing by Subject "Keyphrase extraction"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    Keyphrase extraction through query performance prediction
    (Sage Publications Ltd., 2012) Ercan, G.; Cicekli, I.
    Previous research shows that keyphrases are useful tools in document retrieval and navigation. While these point to a relation between keyphrases and document retrieval performance, no other work uses this relationship to identify keyphrases of a given document. This work aims to establish a link between the problems of query performance prediction (QPP) and keyphrase extraction. To this end, features used in QPP are evaluated in keyphrase extraction using a naïve Bayes classifier. Our experiments indicate that these features improve the effectiveness of keyphrase extraction in documents of different length. More importantly, commonly used features of frequency and first position in text perform poorly on shorter documents, whereas QPP features are more robust and achieve better results. © 2012 The Author(s).
  • Thumbnail Image
    ItemOpen Access
    TurKeyX: Turkish keyphrase extractor
    (IEEE, 2008-10) Kalaycılar, Fırat; Çiçekli, İlyas
    Keyphrases are useful information extracted from documents. They reflect the main ideas of the text. Therefore knowing the list of keyphrases can save substantial amount of time which can be lost during searching for a document about a particular topic. Unfortunately, there are many documents which do not include a list of keyphrases. Thus automatic extraction of keyphrases becomes an important task. In this paper, a method for Turkish keyphrase extraction is explained. © 2008 IEEE.
  • Thumbnail Image
    ItemOpen Access
    Turkish keyphrase extraction using KEA
    (IEEE, 2007-11) Pala, Nagehan; Çiçekli, İlyas
    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. ©2007 IEEE.
  • Thumbnail Image
    ItemOpen Access
    Turkish keyphrase extraction using multi-criterion ranking
    (IEEE, 2009-09) Özdemir, Bahadır; Çiçekli, İlyas
    Keyphrases have been extensively used for indexing and searching in databases and information retrieval systems. In addition, they provide useful information about semantic content of a document. In this paper, we propose an algorithm for automating Turkish keyphrase extraction. Several features of candidate phrases are exploited and form the extraction task as a problem of finding optimal set of candidate phrases. We use multi-criterion ranking to tackle this problem. © 2009 IEEE.