Skills 技能
Goal-oriented bot 面向目标的机器人docs具体介绍
Based on Hybrid Code Networks (HCNs) architecture from Jason D. Williams, Kavosh Asadi, Geoffrey Zweig, Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning – 2017. It allows to predict responses in a goal-oriented dialog. The model is customizable: embeddings, slot filler and intent classifier can be switched on and off on demand.
基于 Jason d. Williams,Kavosh Asadi,Geoffrey Zweig 提出的混合代码网络(Hybrid Code Networks,HCNs)架构,混合代码网络: 实用且高效的端到端对话控制,带有监督和强化学习-2017论文地址。 它允许在一个以目标为导向的对话框中预测回答。 该模型是可定制的: 嵌入,槽填充和意图分类器可以根据需要开关。
Available pre-trained models and their comparison with existing benchmarks:
现有的预先培训模式及其与现有基准的比较,见下图:
其中,bot with slot filler模型地址,
bot with filller & intents & attention模型地址
我们接下来的任务就是研究这个模型