%0 Conference Paper %1 Metzler2005 %A Metzler, Donald %A Bernstein, Yaniv %A Croft, W. Bruce %A Moffat, Alistair %A Zobel, Justin %B CIKM '05: Proceedings of the 14th ACM international conference on Information and knowledge management %C New York, NY, USA %D 2005 %I ACM %K similarity similarity-measure %P 517--524 %R http://doi.acm.org/10.1145/1099554.1099695 %T Similarity measures for tracking information flow %U http://portal.acm.org/ft_gateway.cfm?id=1099695&type=pdf&coll=GUIDE&dl=GUIDE&CFID=40891998&CFTOKEN=51000947 %X Text similarity spans a spectrum, with broad topical similarity near one extreme and document identity at the other. Intermediate levels of similarity -- resulting from summarization, paraphrasing, copying, and stronger forms of topical relevance -- are useful for applications such as information flow analysis and question-answering tasks. In this paper, we explore mechanisms for measuring such intermediate kinds of similarity, focusing on the task of identifying where a particular piece of information originated. We consider both sentence-to-sentence and document-to-document comparison, and have incorporated these algorithms into RECAP, a prototype information flow analysis tool. Our experimental results with RECAP indicate that new mechanisms such as those we propose are likely to be more appropriate than existing methods for identifying the intermediate forms of similarity. %@ 1-59593-140-6

@inproceedings{Metzler2005, abstract = {Text similarity spans a spectrum, with broad topical similarity near one extreme and document identity at the other. Intermediate levels of similarity -- resulting from summarization, paraphrasing, copying, and stronger forms of topical relevance -- are useful for applications such as information flow analysis and question-answering tasks. In this paper, we explore mechanisms for measuring such intermediate kinds of similarity, focusing on the task of identifying where a particular piece of information originated. We consider both sentence-to-sentence and document-to-document comparison, and have incorporated these algorithms into RECAP, a prototype information flow analysis tool. Our experimental results with RECAP indicate that new mechanisms such as those we propose are likely to be more appropriate than existing methods for identifying the intermediate forms of similarity.}, added-at = {2011-07-07T13:40:39.000+0200}, address = {New York, NY, USA}, author = {Metzler, Donald and Bernstein, Yaniv and Croft, W. Bruce and Moffat, Alistair and Zobel, Justin}, biburl = {https://www.bibsonomy.org/bibtex/2aaea952a59109145294ddc2080731da0/stroeh}, booktitle = {CIKM '05: Proceedings of the 14th ACM international conference on Information and knowledge management}, doi = {http://doi.acm.org/10.1145/1099554.1099695}, interhash = {596368e03603f63695cb256d6e41603e}, intrahash = {aaea952a59109145294ddc2080731da0}, isbn = {1-59593-140-6}, keywords = {similarity similarity-measure}, location = {Bremen, Germany}, pages = {517--524}, publisher = {ACM}, timestamp = {2011-07-07T13:40:39.000+0200}, title = {Similarity measures for tracking information flow}, url = {http://portal.acm.org/ft_gateway.cfm?id=1099695&type=pdf&coll=GUIDE&dl=GUIDE&CFID=40891998&CFTOKEN=51000947}, year = 2005 }