%Aigaion2 BibTeX export from Idiap Publications
%Monday 04 March 2024 09:55:34 AM

@INPROCEEDINGS{grangier:2005:cikm,
         author = {Grangier, David and Bengio, Samy},
       projects = {Idiap},
          month = {10},
          title = {Inferring Document Similarity from Hyperlinks},
      booktitle = {ACM Conference on Information and Knowledge Management},
           year = {2005},
        address = {Bremen, Germany},
       crossref = {grangier:2005:idiap-05-21},
       abstract = {Assessing semantic similarity between text documents is a crucial aspect in Information Retrieval systems. In this work, we propose to use hyperlink information to derive a similarity measure that can then be applied to compare any text documents, with or without hyperlinks. As linked documents are generally semantically closer than unlinked documents, we use a training corpus with hyperlinks to infer a function $a,b \to sim(a,b)$ that assigns a higher value to linked documents than to unlinked ones. Two sets of experiments on different corpora show that this function compares favorably with {\em OKAPI} matching on document retrieval tasks.},
            pdf = {https://publications.idiap.ch/attachments/reports/2005/grangier-2005-cikm.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2005/grangier-2005-cikm.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{grangier:2005:idiap-05-21,
         author = {Grangier, David and Bengio, Samy},
       projects = {Idiap},
          title = {Inferring Document Similarity from Hyper-links},
           type = {Idiap-RR},
         number = {Idiap-RR-21-2005},
           year = {2005},
    institution = {IDIAP},
       abstract = {Assessing semantic similarity between text documents is a crucial aspect in Information Retrieval systems. In this paper, we propose a technique to derive a similarity measure from hyper-link information. As linked documents are generally semantically closer than unlinked documents, we use a training corpus with hyper-links to infer a function $a,b \to sim(a,b)$ that assigns a higher value to linked documents than to unlinked ones. Two sets of experiments on different corpora show that this function compares favorably with {\em OKAPI} matching on document retrieval tasks.},
            pdf = {https://publications.idiap.ch/attachments/reports/2005/grangier-rr-05-21.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2005/grangier-rr-05-21.ps.gz},
ipdmembership={speech},
}