Learning Transformation Rules by Examples

Wu, Bo (University of Southern California) | Szekely, Pedro (University of Southern California) | Knoblock, Craig A. (University of Southern California)

AAAI Conferences 

However, this approach usually requires expert users to write individual transformations for each data source manually. Figure 2: Delete grammar A variety of work (Kandel et al. 2011; Raman and Hellerstein 2001; Liang, Jordan, and Klein 2010) tries to take advantage of user input to solve the transformation problem, cally learn transformation rules through examples. As shown but these methods either cannot learn rules from training in Figure 1, a user might want to reverse the order of the date data or need the training data to contain all the intermediate and use hyphens to replace slashes. The user would just provide steps. We have developed an approach where the user the system with an example "30/07/2010" and "2010-only needs to provide the target value as an example.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found