论文信息 - Automatic keyword extraction for learning object repositories

Automatic keyword extraction for learning object repositories

The paper describes experiments in metadata generation for learning object repositories. Specifically, we present several methods for automatic keyword extraction and evaluate them on a collection of learning objects from an undergraduate history course. The results suggest that automatic keyword extraction is a viable solution for suggesting terms and phrases for metadata annotation.

William E. Moen | Rada Mihalcea | Kino Coursey

[1] David Wiley,et al. Connecting learning objects to instructional design theory: A definition, a metaphor, and a taxonomy , 2000 .

[2] Massimo Marchiori,et al. The Limits of Web Metadata, and Beyond , 1998, Comput. Networks.

[3] Jane Greenberg,et al. Final Report for the AMeGA (Automatic Metadata Generation Applications) Project , 2005 .

[4] Michael J. Fischer,et al. The String-to-String Correction Problem , 1974, JACM.

[5] Peter D. Turney. Learning to Extract Keyphrases from Text , 2002, ArXiv.

[6] Anette Hulth,et al. Improved Automatic Keyword Extraction Given More Linguistic Knowledge , 2003, EMNLP.

[7] Sergey Brin,et al. The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[8] Rada Mihalcea,et al. Linking Educational Materials to Encyclopedic Knowledge , 2007, AIED.

[9] Carl Gutwin,et al. Domain-Specific Keyphrase Extraction , 1999, IJCAI.

[10] Rada Mihalcea,et al. TextRank: Bringing Order into Text , 2004, EMNLP.

[11] Costas S. Iliopoulos,et al. Algorithms for computing variants of the longest common subsequence problem , 2008, Theor. Comput. Sci..