This work proposes a novel metric, Maximally Amortized Cost (MAC), for cost evaluations of error correction of predictive Chinese input methods (IMs). With a series of real-time simulation, user correction behaviors are analyzed by estimating generalized backward compatibility of adaptive Chinese IMs. Comparisons between three IMs by using MAC with different context lengths report empirical factors of context length for improving predictive IMs. The error-tolerance level—Futile Effort, Beneficial Effort and Utility—of adaptive IMs is also proposed and analyzed.
|Title of host publication||Workshop on Advances in Text Input Methods (WTIM)|
|Publication status||Published - Dec 2011|