论文标题
对话历史记录整合到端到端的信号到概念语言理解系统
Dialogue history integration into end-to-end signal-to-concept spoken language understanding systems
论文作者
论文摘要
这项工作调查了代表对话式语言理解（SLU）系统中对话历史的嵌入。当通过单个端到端神经网络模型直接从语音信号中提取语义信息时，我们将重点放在场景上。我们建议将对话历史记录整合到端到端的信号到概念slu系统中。对话框历史记录以对话框历史记录嵌入向量（所谓的H-向量）的形式表示，并作为端到端SLU模型的附加信息提供，以提高系统性能。提出了以下三种类型的H-媒介，并在本文中对实验进行了评估：（1）所有嵌入式的嵌入式预测用户在最后的对话系统响应中的回答中预期的概念袋； （2）侧重于仅预测选定的语义概念集（对应于我们实验中最常见的错误）的监督Freq嵌入式； （3）无监督的嵌入。在媒体语料库上进行语义插槽填充任务的实验表明，所提出的H-矢量可以改善模型性能。
This work investigates the embeddings for representing dialog history in spoken language understanding (SLU) systems. We focus on the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. We proposed to integrate dialogue history into an end-to-end signal-to-concept SLU system. The dialog history is represented in the form of dialog history embedding vectors (so-called h-vectors) and is provided as an additional information to end-to-end SLU models in order to improve the system performance. Three following types of h-vectors are proposed and experimentally evaluated in this paper: (1) supervised-all embeddings predicting bag-of-concepts expected in the answer of the user from the last dialog system response; (2) supervised-freq embeddings focusing on predicting only a selected set of semantic concept (corresponding to the most frequent errors in our experiments); and (3) unsupervised embeddings. Experiments on the MEDIA corpus for the semantic slot filling task demonstrate that the proposed h-vectors improve the model performance.
