We present the first complete attempt at concurrently training conversational
agents that communicate only via self-generated language. Using DSTC2 as seed
data, we trained natural language understanding (NLU) and generation (NLG)
networks for each agent and let the agents interact online. We model the
interaction as a stochastic collaborative game where each agent (player) has a
role ("assistant", "tourist", "eater", etc.) and their own objectives, and can
only interact via natural language they generate. Each agent, therefore, needs
to learn to operate optimally in an environment with multiple sources of
uncertainty (its own NLU and NLG, the other agent's NLU, Policy, and NLG). In
our evaluation, we show that the stochastic-game agents outperform deep
learning based supervised baselines.

本文利用 DSTC2 数据为种子数据，建立了功能包括：natural language understanding 和 natural language generation 的 conversational agent，并让它们通过生成自然语言进行在线交互，进而将这个交互行为建模成一个随机协作游戏，并在实验中表现出优于 deep learning 的结果。