Extraction of Keyphrases from Text: Evaluation of Four Algorithms Export

@misc{citeulike:111659, abstract = {This report presents an empirical evaluation of four algorithms for automatically extracting keywords and keyphrases from documents. The four algorithms are compared using five different collections of documents. For each document, we have a target set of keyphrases, which were generated by hand. The target keyphrases were generated for human readers; they were not tailored for any of the four keyphrase extraction algorithms. Each of the algorithms was evaluated by the degree to which the algorithm's keyphrases matched the manually generated keyphrases. The four algorithms were (1) the AutoSummarize feature in Microsoft's Word 97, (2) an algorithm based on Eric Brill's part-of-speech tagger, (3) the Summarize feature in Verity's Search 97, and (4) NRC's Extractor algorithm. For all five document collections, NRC's Extractor yields the best match with the manually generated keyphrases.}, archivePrefix = {arXiv}, author = {Turney, Peter D.}, citeulike-article-id = {111659}, citeulike-linkout-0 = {http://arxiv.org/abs/cs/0212014}, citeulike-linkout-1 = {http://arxiv.org/pdf/cs/0212014}, day = {8}, eprint = {cs/0212014}, keywords = {algorithm, evaluation, extraction, keyphrase, text}, month = {December}, posted-at = {2006-03-17 08:55:55}, priority = {5}, title = {Extraction of Keyphrases from Text: Evaluation of Four Algorithms}, url = {http://arxiv.org/abs/cs/0212014}, year = {2002} }

TY - ELEC ID - citeulike:111659 L3 - citeulike-article-id:111659 N2 - This report presents an empirical evaluation of four algorithms for automatically extracting keywords and keyphrases from documents. The four algorithms are compared using five different collections of documents. For each document, we have a target set of keyphrases, which were generated by hand. The target keyphrases were generated for human readers; they were not tailored for any of the four keyphrase extraction algorithms. Each of the algorithms was evaluated by the degree to which the algorithm's keyphrases matched the manually generated keyphrases. The four algorithms were (1) the AutoSummarize feature in Microsoft's Word 97, (2) an algorithm based on Eric Brill's part-of-speech tagger, (3) the Summarize feature in Verity's Search 97, and (4) NRC's Extractor algorithm. For all five document collections, NRC's Extractor yields the best match with the manually generated keyphrases. TI - Extraction of Keyphrases from Text: Evaluation of Four Algorithms KW - algorithm KW - evaluation KW - extraction KW - keyphrase KW - text AU - Turney, Peter PY - 2002/12/08/ UR - http://arxiv.org/abs/cs/0212014 ER -