@incollection{noKey,
  abstract = {Long-term Web archives comprise Web documents gathered over longer time periods and can easily reach hundreds of terabytes in size. Semantic annotations such as named entities can facilitate intelligent access to the Web archive data. However, the annotation of the entire archive content on this scale is often infeasible. The most efficient way to access the documents within Web archives is provided through their URLs, which are typically stored in dedicated index files. The URLs of the archived Web documents can contain semantic information and can offer an efficient way to obtain initial semantic annotations for the archived documents. In this paper, we analyse the applicability of semantic analysis techniques such as named entity extraction to the URLs in a Web archive. We evaluate the precision of the named entity extraction from the URLs in the GermanWeb dataset and analyse the proportion of the archived URLs from 1,444 popular domains in the time interval from 2000 to 2012 to which these techniques are applicable. Our results demonstrate that named entity recognition can be successfully applied to a large number of URLs in our Web archive and provide a good starting point to efficiently annotate large scale collections of Web documents.},
  added-at = {2016-01-18T14:39:56.000+0100},
  author = {Souza, Tarcisio and Demidova, Elena and Risse, Thomas and Holzmann, Helge and Gossen, Gerhard and Szymanski, Julian},
  biburl = {https://www.bibsonomy.org/bibtex/2e2b7a71a74ed4ebf37b0054f1cce7e33/trisse69},
  booktitle = {Semantic Keyword-based Search on Structured Data Sources},
  doi = {10.1007/978-3-319-27932-9_14},
  editor = {Cardoso, Jorge and Guerra, Francesco and Houben, Geert-Jan and Pinto, Alexandre Miguel and Velegrakis, Yannis},
  interhash = {9ccf945cea9ad693553ec106fc8fe07c},
  intrahash = {e2b7a71a74ed4ebf37b0054f1cce7e33},
  isbn = {978-3-319-27931-2},
  keywords = {URL annotation icrawl myown webarchiving},
  language = {English},
  pages = {153-166},
  publisher = {Springer International Publishing},
  series = {Lecture Notes in Computer Science},
  timestamp = {2016-01-18T14:39:56.000+0100},
  title = {Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives},
  url = {http://dx.doi.org/10.1007/978-3-319-27932-9_14},
  volume = 9398,
  year = 2015
}