论文标题
从任务专业的对话代理人合奏的弱监督的神经反应选择
Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents
论文作者
论文摘要
对话引擎结合了不同类型的代理与人类交谈的引擎很受欢迎。 但是，对话是动态的，从某种意义上说，选定的响应将改变对话，从而影响了对话中的后续话语，这使得响应选择成为一个具有挑战性的问题。 我们通过考虑对话历史记录，从一组异质对话代理产生的一组响应中选择最佳响应的问题，并提出\ emph {neural响应选择}方法。 培训了所提出的方法，以预测单个对话中的一组连贯的响应集，并通过课程培训机制考虑了自己的预测。 我们的实验结果表明，所提出的方法可以准确选择最合适的响应，从而显着改善对话系统中的用户体验。
Dialogue engines that incorporate different types of agents to converse with humans are popular. However, conversations are dynamic in the sense that a selected response will change the conversation on-the-fly, influencing the subsequent utterances in the conversation, which makes the response selection a challenging problem. We model the problem of selecting the best response from a set of responses generated by a heterogeneous set of dialogue agents by taking into account the conversational history, and propose a \emph{Neural Response Selection} method. The proposed method is trained to predict a coherent set of responses within a single conversation, considering its own predictions via a curriculum training mechanism. Our experimental results show that the proposed method can accurately select the most appropriate responses, thereby significantly improving the user experience in dialogue systems.
