Toward Scalable Neural Dialogue State Tracking Model
Toward Scalable Neural Dialogue State Tracking Model
复制标题
迈向可扩展的神经对话状态跟踪模型
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Ehsan Hosseini
中科院分区：
文献类型：
--
作者：
E. Nouri;Ehsan Hosseini
当前基于神经的对话状态跟踪模型中的延迟限制了它们在生产系统中的有效使用，尽管它们的性能非常准确。在钟等人最近提出的全局-局部自主注意编码器模型的基础上，提出了一种新的可扩展且精确的神经对话状态跟踪模型。它使用全局模块在不同类型(称为时隙)的对话状态的估计器之间共享参数，并使用局部模块来学习特定于时隙的特征。与GREAD模型中使用的(1+#个槽)具有全局和局部条件的递归网络相比，该模型仅使用一个带有全局条件化的递归网络，在保持信念状态跟踪性能的同时，训练和推理时间平均减少了$35$，转向请求时减少了$97.38\$，联合目标和准确率减少了$88.51\$。在多域数据集上的评估也表明，该模型在转向信息和联合目标精度方面优于GREAD。
The latency in the current neural based dialogue state tracking models prohibits them from being used efficiently for deployment in production systems, albeit their highly accurate performance. This paper proposes a new scalable and accurate neural dialogue state tracking model, based on the recently proposed Global-Local Self-Attention encoder (GLAD) model by Zhong et al. which uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. By using only one recurrent networks with global conditioning, compared to (1 + # slots) recurrent networks with global and local conditioning used in the GLAD model, our proposed model reduces the latency in training and inference times by $35\%$ on average, while preserving performance of belief state tracking, by $97.38\%$ on turn request and $88.51\%$ on joint goal and accuracy. Evaluation on Multi-domain dataset (Multi-WoZ) also demonstrates that our model outperforms GLAD on turn inform and joint goal accuracy.