论文标题
通过多任务学习重新构图对话处理的增量深度语言模型
Re-framing Incremental Deep Language Models for Dialogue Processing with Multi-task Learning
论文作者
论文摘要
我们提出了一个多任务学习框架，以实现一个通用增量对话处理模型的培训，该模型具有四个不足的检测任务，语言建模，词性标记和话语细分，并在简单的深度循环环境中进行。我们表明，这些任务彼此提供了积极的归纳偏见，而每个任务的最佳贡献依赖于任务中噪声的严重性。我们的现场多任务模型优于类似的单个任务，提供竞争性能，并且对在精神病治疗中的对话剂中的未来使用是有益的。
We present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging, and utterance segmentation in a simple deep recurrent setting. We show that these tasks provide positive inductive biases to each other with the optimal contribution of each one relying on the severity of the noise from the task. Our live multi-task model outperforms similar individual tasks, delivers competitive performance, and is beneficial for future use in conversational agents in psychiatric treatment.
