Recursive extraction and narration of nested tables

作者: Ashish Mungi , Purushothaman K. Narayanan , Krishma Singla , Bijo A. Thomas

DOI:

关键词:

摘要: Machine logic (for example, software) that performs the following steps: (i) providing a parent table including set of nested table(s) so has N levels nestedness, with being an integer greater than one; and (ii) extracting first at Nth level nestedness where is equal to or one, value one representing root table, values tables within table; (iii) replacing equivalent narration text. Software agnostic respect having different structural patterns, file formats, and/or cell layouts.

参考文章(6)
Shah Khusro, Asima Latif, Irfan Ullah, On methods and tools of table detection, extraction and annotation in PDF documents Journal of Information Science. ,vol. 41, pp. 41- 57 ,(2015) , 10.1177/0165551514551903
Helmut Hofmann, Markus Koenigstein, System and method for simultaneous display of multiple tables ,(2011)
Cui Tao, David W. Embley, Automatic hidden-web table interpretation, conceptualization, and semantic annotation data and knowledge engineering. ,vol. 68, pp. 683- 703 ,(2009) , 10.1016/J.DATAK.2009.02.010
Jesse D. McGatha, Khaled S. Sedky, Oliver H. Foehr, Ahmet Gurcan, Eric S. Leese, Rodrigo Lopez, Jeffrey G. Brown, Ming Liu, Jerry J. Dunietz, Analyzing lines to detect tables in documents ,(2006)
James P. Finnigan, Vivek R. Narasayya, Kris Ganjam, Zhimin Chen, Kaushik Chakrabarti, Surajit Chaudhuri, Kanstantsyn Zoryn, Annotating structured data for search ,(2014)
Matthew S. Chmiel, David Dewar, Christopher David Burt, Ryan Christopher Mccluskey, Syed Ali Haider, Responsive data exploration on small screen devices ,(2015)