This paper analyzes the productivity growth in Korean agriculture with data on multiple crops over the five years from 1998 to 2002. Measurements are obtained from the estimation of a non-frontier multi-output production function. Multi-output production technology is characterized with a transformation function. For empirical analysis, this study employs the generalized linear transformation function, which extends a linear functional form by allowing a full set of interactions among arguments in the function. The results find that technological change has led a significant productivity change. Larger farms experience the highest rate of productivity growth by the greatest rate of scale effect. More human capital also leads higher productivity growth rates.