Learning Autocomplete Systems as a Communication Game
This work addresses the challenge of improving autocomplete systems for users by enhancing communication efficiency and accuracy, though it is incremental in its method.
The paper tackles the problem of textual autocomplete by framing it as a human-machine communication game, balancing efficiency, accuracy, and interpretability. The proposed unsupervised approach achieves 52% higher accuracy at a given efficiency level and reduces typing time by nearly 50% compared to full sentences.
We study textual autocomplete---the task of predicting a full sentence from a partial sentence---as a human-machine communication game. Specifically, we consider three competing goals for effective communication: use as few tokens as possible (efficiency), transmit sentences faithfully (accuracy), and be learnable to humans (interpretability). We propose an unsupervised approach which tackles all three desiderata by constraining the communication scheme to keywords extracted from a source sentence for interpretability and optimizing the efficiency-accuracy tradeoff. Our experiments show that this approach results in an autocomplete system that is 52% more accurate at a given efficiency level compared to baselines, is robust to user variations, and saves time by nearly 50% compared to typing full sentences.