Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
复制标题
DOI：
--
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
T. Conley
中科院分区：
文献类型：
--
作者：
T. Conley
尽管人们有能力在不努力的情况下进行Vapid对话，但这可能不是一个独特的人类特征。自1960年代以来，研究人员一直在努力创建可以产生人造对话的代理商。这些程序通常称为聊天机器人。随着神经网络用于对话的生成，一些人得出结论，已经实现了这一目标。这项研究通过创建一个对话框生成复发性神经网络（RNN），并通过辅助损失功能和梁搜索来增强该网络的能力，从而加入了任务。我们的自定义损失功能通过包括最大互信息（MMI）和熵的计算来实现更好的内聚力和连贯性。我们通过使用一组以先前的研究和基于自然语言处理的久经考验原则的启发来证明该系统的有效性。
Although people have the ability to engage in vapid dialogue without effort, this may not be a uniquely human trait. Since the 1960's researchers have been trying to create agents that can generate artificial conversation. These programs are commonly known as chatbots. With increasing use of neural networks for dialog generation, some conclude that this goal has been achieved. This research joins the quest by creating a dialog generating Recurrent Neural Network (RNN) and by enhancing the ability of this network with auxiliary loss functions and a beam search. Our custom loss functions achieve better cohesion and coherence by including calculations of Maximum Mutual Information (MMI) and entropy. We demonstrate the effectiveness of this system by using a set of custom evaluation metrics inspired by an abundance of previous research and based on tried-and-true principles of Natural Language Processing.