It is possible to automatically annotate a natural science spreadsheet using lexical matching, given that the tables in these spreadsheets meet a number of requirements regarding the content. Results of a survey show that most of the existing natural science spreadsheets deviate from the ideal situation. We propose to complement lexical matching with both heuristics and knowledge from external vocabularies to overcome these deviations.
|Journal||CEUR Workshop Proceedings|
|Publication status||Published - 1 Jan 2017|
- Domain knowledge
- Knowledge engineering