481-W13-slyngbae-FacebookGraphSearchVsGoogleKnowledgeGrah

Natural language processing is a subset of the field of artificial intelligence. It focuses on the interaction between computers and natural human language. Since natural language is not structured, it is not something that computers can easily understand. This makes it hard for computers to derive meaning out of natural language. Although we have already gone over the basics of natural language processing (Kim's presentation), there are several subfields that explore different areas of the topic. Some of these fields are optical character recognition, parsing, question answering systems, information retrieval, word sense disambiguation, and automatic summarization. The area of focus for this presentation is automatic summarization. Within the field of text summarization there are two main approaches involved: extractive, and abstractive. The extractive approach deals with highlighting the important keywords or key-sentences within a text and choosing those as candidates for a summary. The hard task is to determine which sentences or keywords are salient and how to eliminate redundancy within the summary. The abstractive approach deals with getting a semantic understanding of the text and relying on natural language generation (NLG) to create novel sentences and summaries. The presentation goes into depth of each of these two approaches, their pros and cons, and some sub-topics within the field. Sources: G. Erkan and D. R. Radev. Lexrank: graph-based lexical centrality as salience in text summarization. J. Artif. Int. Res., 22(1):457{479, Dec. 2004. M. Hu, A. Sun, and E.-P. Lim. Comments-oriented blog summarization by sen- tence extraction. In Proceedings of the sixteenth ACM conference on Confer- ence on information and knowledge management, CIKM '07, pages 901{904, New York, NY, USA, 2007. ACM. M. Hu, A. Sun, and E.-P. Lim. Comments-oriented document summarization: un- derstanding documents with readers' feedback. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in informa- tion retrieval, SIGIR '08, pages 291{298, New York, NY, USA, 2008. ACM. Y. Lu, C. Zhai, and N. Sundaresan. Rated aspect summarization of short com- ments. In Proceedings of the 18th international conference on World wide web, WWW '09, pages 131{140, New York, NY, USA, 2009. ACM. M. Potthast and S. Becker. Opinion summarization of web comments. In Pro- 6IBLIOGRAPHY 7 ceedings of the 32nd European conference on Advances in Information Retrieval, ECIR'2010, pages 668{669, Berlin, Heidelberg, 2010. Springer-Verlag. Z. Ren, J. Ma, S. Wang, and Y. Liu. Summarizing web forum threads based on a latent topic propagation process. In Proceedings of the 20th ACM international conference on Information and knowledge management, CIKM '11, pages 879{ 884, New York, NY, USA, 2011. ACM. Mihalcea, Rada. TextRank: Bringing Order into Texts. [Stroudsburg, Pennsylvania]. UNT Digital Library.<a rel="nofollow" class="external free" href="http://digital.library.unt.edu/ark:/67531/metadc30962/">http://digital.library.unt.edu/ark:/67531/metadc30962/</a>. Accessed November 20, 2012.