论文信息 - Automating the Selection of Storiesfor AI in the News

Automating the Selection of Storiesfor AI in the News

It is relatively easy, albeit time-consuming, for a person to find and select news stories that meet subjective judgments of relevance and interest to a community.NewsFinder is an AI program that automates the steps involved in this task, from crawling the web to publishing the results.NewsFinder incorporates a learning program whose judgment of interestingness of stories can be trained by feedback from readers.Preliminary testing confirms the feasibility of automating the service to write AI in the News for the AAAI.

[1] Paul Resnick,et al. Recommender systems , 1997, CACM.

[2] Wei-Ying Ma,et al. Learning block importance models for web pages , 2004, WWW '04.

[3] Gerard Salton,et al. Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..

[4] Steven Bird,et al. NLTK: The Natural Language Toolkit , 2002, ACL.

[5] Fillia Makedon,et al. Learning from Incomplete Ratings Using Non-negative Matrix Factorization , 2006, SDM.

[6] Gail E. Kaiser,et al. DOM-based content extraction of HTML documents , 2003, WWW '03.

[7] Geoffrey I. Webb,et al. Encyclopedia of Machine Learning , 2011, Encyclopedia of Machine Learning.

[8] Bruce G. Buchanan,et al. The AAAI Video Archive , 2008, AI Mag..

[9] Jonathan L. Herlocker,et al. Evaluating collaborative filtering recommender systems , 2004, TOIS.