TL;DR本文研究 Dialogue Act 分类,提出了将上下文感知的自注意机制与分层循环神经网络相结合的方法,并在 SwDA Corpus 上证明了其在不同语义表征学习方法下的高精度表现。
Abstract
Recent work in dialogue act classification has treated the task as a sequence
labeling problem using hierarchical deep neural networks. We build on this
prior work by leveraging the effectiveness of a context-awa