%Aigaion2 BibTeX export from Knowledge Engineering Publications
%Friday 17 December 2021 11:58:28 PM

@TECHREPORT{jf:TUD-KE-2008-05,
       author = {Weizs{\"{a}}cker, Lorenz and F{\"{u}}rnkranz, Johannes},
        title = {On Table Extraction from Text Sources with Markups},
       number = {TUD-KE-2008-05},
         year = {2008},
  institution = {TU Darmstadt, Knowledge Engineering Group},
          url = {/publications/reports/tud-ke-2008-05.pdf},
     abstract = {Table extraction is the task of locating tables in documents and extracting their entries along with the arrangement of the entries inside the tables. The notion of tables applied in this work excludes any sort of meta data, e.g. only the content elements of the tables are to be extracted. We follow a simple unsupervised approach by selecting the tables according to a score that measures the in-column consistency as pairwise similarities of entries where  separators columns are also taken into account. Since the average is less reliable for smaller table this score demands a levelling in favor of greater tables for which we make different propositions that are covered by experiments on a test set of HTML documents. In order to reduce the number of candidate tables we use assumptions on the entry borders in terms of markup tags. They only hold for a part of the test set but allow us to evaluate any potential table without referring to the HTML syntax. The experiments show that the discriminative power of the in-column similarities are limited but also considerable given the simplicity of the applied similarity functions.}
}