TU Darmstadt / ULB / TUbiblio

On Table Extraction from Text Sources with Markups

Weizsäcker, Lorenz and Fürnkranz, Johannes (2008):
On Table Extraction from Text Sources with Markups.
[Online-Edition: http://www.ke.informatik.tu-darmstadt.de/publications/report...],
[Report]

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.

Item Type: Report
Erschienen: 2008
Creators: Weizsäcker, Lorenz and Fürnkranz, Johannes
Title: On Table Extraction from Text Sources with Markups
Language: English
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.

Divisions: 20 Department of Computer Science
20 Department of Computer Science > Knowl­edge En­gi­neer­ing
Date Deposited: 24 Jun 2011 15:11
Official URL: http://www.ke.informatik.tu-darmstadt.de/publications/report...
Identification Number: TUD-KE-2008-05
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)

View Item View Item