Multitask Learning for Spoken Language Understanding
Multitask Learning for Spoken Language Understanding
复制标题
口语理解的多任务学习
DOI：
10.1109/icassp.2006.1660088
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
Gökhan Tür
中科院分区：
文献类型：
--
作者：
Gökhan Tür
在本文中，我们提出了一种多任务学习（MTL）方法，用于目标导向的人机口语对话系统中的意图分类。 MTL 的目标是在使用共享表示的同时并行训练任务。每项任务学到的东西可以帮助更好地学习其他任务。我们的目标是自动重用来自各种应用程序的现有标记数据，这些数据相似但可能具有不同的意图或意图分布，以提高性能。为此，我们提出了一种跨应用程序的自动意图映射算法。我们还建议采用主动学习来选择性地对要重复使用的数据进行采样。我们的结果表明，我们可以显着提高意图分类性能，尤其是当标记数据大小有限时
In this paper, we present a multitask learning (MTL) method for intent classification in goal oriented human-machine spoken dialog systems. MTL aims at training tasks in parallel while using a shared representation. What is learned for each task can help other tasks be learned better. Our goal is to automatically re-use the existing labeled data from various applications, which are similar but may have different intents or intent distributions, in order to improve the performance. For this purpose, we propose an automated intent mapping algorithm across applications. We also propose employing active learning to selectively sample the data to be re-used. Our results indicate that we can achieve significant improvements in intent classification performance especially when the labeled data size is limited