Automatic extraction of document keyphrases for use in digital libraries: Evaluation and applications Export

@article{citeulike:4233061, abstract = {This article describes an evaluation of the Kea automatic keyphrase extraction algorithm. Document keyphrases are conventionally used as concise descriptors of document content, and are increasingly used in novel ways, including document clustering, searching and browsing interfaces, and retrieval engines. However, it is costly and time consuming to manually assign keyphrases to documents, motivating the development of tools that automatically perform this function. Previous studies have evaluated Kea's performance by measuring its ability to identify author keywords and keyphrases, but this methodology has a number of well-known limitations. The results presented in this article are based on evaluations by human assessors of the quality and appropriateness of Kea keyphrases. The results indicate that, in general, Kea produces keyphrases that are rated positively by human assessors. However, typical Kea settings can degrade performance, particularly those relating to keyphrase length and domain specificity. We found that for some settings, Kea's performance is better than that of similar systems, and that Kea's ranking of extracted keyphrases is effective. We also determined that author-specified keyphrases appear to exhibit an inherent ranking, and that they are rated highly and therefore suitable for use in training and evaluation of automatic keyphrasing systems.}, address = {Department of Computer Science, University of Waikato, Private Bag 3105, Hamilton, New Zealand.}, author = {Jones, Steve and Paynter, Gordon W.}, citeulike-article-id = {4233061}, citeulike-linkout-0 = {http://dx.doi.org/10.1002/asi.10068}, citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/93513056/ABSTRACT}, doi = {10.1002/asi.10068}, issn = {1532-2890}, journal = {Journal of the American Society for Information Science and Technology}, keywords = {is364}, number = {8}, pages = {653--677}, posted-at = {2009-10-14 05:52:58}, priority = {2}, title = {Automatic extraction of document keyphrases for use in digital libraries: Evaluation and applications}, url = {http://dx.doi.org/10.1002/asi.10068}, volume = {53}, year = {2002} }

TY - JOUR ID - citeulike:4233061 L3 - citeulike-article-id:4233061 N2 - This article describes an evaluation of the Kea automatic keyphrase extraction algorithm. Document keyphrases are conventionally used as concise descriptors of document content, and are increasingly used in novel ways, including document clustering, searching and browsing interfaces, and retrieval engines. However, it is costly and time consuming to manually assign keyphrases to documents, motivating the development of tools that automatically perform this function. Previous studies have evaluated Kea's performance by measuring its ability to identify author keywords and keyphrases, but this methodology has a number of well-known limitations. The results presented in this article are based on evaluations by human assessors of the quality and appropriateness of Kea keyphrases. The results indicate that, in general, Kea produces keyphrases that are rated positively by human assessors. However, typical Kea settings can degrade performance, particularly those relating to keyphrase length and domain specificity. We found that for some settings, Kea's performance is better than that of similar systems, and that Kea's ranking of extracted keyphrases is effective. We also determined that author-specified keyphrases appear to exhibit an inherent ranking, and that they are rated highly and therefore suitable for use in training and evaluation of automatic keyphrasing systems. IS - 8 JF - Journal of the American Society for Information Science and Technology SN - 1532-2890 AD - Department of Computer Science, University of Waikato, Private Bag 3105, Hamilton, New Zealand. EP - 677 TI - Automatic extraction of document keyphrases for use in digital libraries: Evaluation and applications VL - 53 SP - 653 KW - is364 AU - Jones, Steve AU - Paynter, Gordon PY - 2002/// UR - http://dx.doi.org/10.1002/asi.10068 ER -