Conundrums in Unsupervised Keyphrase Extraction: Making Sense of the State-of-the-Art

State-of-the-art approaches for unsupervised keyphrase extraction are typically evaluated on a single dataset with a single parameter setting. Consequently, it is unclear how effective these approaches are on a new dataset from a different domain, and how sensitive they are to changes in parameter settings. To gain a better understanding of state-of-the-art unsupervised keyphrase extraction algorithms, we conduct a systematic evaluation and analysis of these algorithms on a variety of standard evaluation datasets.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Kazi Saidul Hasan, Vincent Ng
• Keywords: COLING 2010, Computational Linguistics, Standard Evaluation Datasets, State-of-the-art Unsupervised Keyphrase, Unsupervised Keyphrase Extraction