Learning Autocomplete Systems as a Communication Game
arXiv:1911.06964
Abstract
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.
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Effective Approaches to Attention-based Neural Machine Translation
- Learning Multiagent Communication with Backpropagation
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
- Language as a Latent Variable: Discrete Generative Models for Sentence Compression
- Unsupervised Sentence Compression using Denoising Auto-Encoders