BibSonomyburst/bibtex/1bdcca006bcc7bd1cc169f926adbe43dbBibSonomy RSS feed for /bibtex/1bdcca006bcc7bd1cc169f926adbe43db2012-02-17T09:36:23+01:00http://www.bibsonomy.org/bibtex/252596434ca2a991b56dff2f52ab5ac94/dblpdblp2011-12-23T00:00:00+01:00dblp <span class="authorEditorList"><a href="/author/Mani">Inderjeet Mani</a>, and <a href="/author/Bloedorn">Eric Bloedorn</a> </span><em>AAAI/IAAI, </em><em>page 622-628. </em><em>AAAI Press / The MIT Press, </em>(<em>1997</em>)Fri Dec 23 00:00:00 CET 2011AAAI/IAAIconf/aaai/1997622-628Multi-Document Summarization by Graph Search and Matching.1997dblp http://www.bibsonomy.org/bibtex/287535fc865377ad1ff4d3274c10de5eb/dblpdblp2011-12-05T00:00:00+01:00dblp <span class="authorEditorList"><a href="/author/Mani">Inderjeet Mani</a>, and <a href="/author/Bloedorn">Eric Bloedorn</a> </span><em>CoRR</em> (<em>1997</em>)Mon Dec 05 00:00:00 CET 2011CoRRMulti-document Summarization by Graph Search and Matchingcmp-lg/97120041997dblp http://www.bibsonomy.org/bibtex/26f8b5bca8a7c32f872b317e2e19880bc/llemelleme2010-10-17T02:10:38+02:00summarization <span class="authorEditorList"><a href="/author/Mani">Inderjeet Mani</a>, and <a href="/author/Bloedorn">Eric Bloedorn</a> </span><em>Proc. of the 14th National Conf. on Artificial Intelligence AAAI, </em><em>page 622-628. </em>(<em>1997</em>)Sun Oct 17 02:10:38 CEST 2010Proc. of the 14th National Conf. on Artificial Intelligence (AAAI)622-628Multi-Document Summarization by Graph Search and Matching1997summarization We describe a new method for summarizing similarities and differences in a pair of related documents using a graph representation for text. Concepts denoted by words, phrases, and proper names in the document are represented positionally as nodes in the graph along with edges corresponding to semantic relations between items. Given a perspective in terms of which the pair of documents is to be summarized, the algorithm first uses a spreading activation technique to discover, in each document, nodes semantically related to the topic. The activated graphs of each document are then matched to yield a graph corresponding to similarities and differences between the pair, which is rendered in natural language. An evaluation of these techniques has been carried out.http://www.bibsonomy.org/bibtex/287535fc865377ad1ff4d3274c10de5eb/diego_madiego_ma2008-02-26T06:39:48+01:00graphs summarisation <span class="authorEditorList"><a href="/author/Mani">Inderjeet Mani</a>, and <a href="/author/Bloedorn">Eric Bloedorn</a> </span><em>CoRR</em> (<em>1997</em>)<em>informal publication . </em>Tue Feb 26 06:39:48 CET 2008CoRRinformal publicationMulti-document Summarization by Graph Search and Matchingcmp-lg/97120041997graphs summarisation We describe a new method for summarizing similarities and differences in a pair of related documents using a graph representation for text. Concepts denoted by words, phrases, and proper names in the document are represented positionally as nodes in the graph along with edges corresponding to semantic relations between items. Given a perspective in terms of which the pair of documents is to be summarized, the algorithm first uses a spreading activation technique to discover, in each document, nodes semantically related to the topic. The activated graphs of each document are then matched to yield a graph corresponding to similarities and differences between the pair, which is rendered in natural language. An evaluation of these techniques has been carried out.