Neural-based Context Representation Learning for Dialog Act Classification
This work addresses dialog act classification for natural language processing applications, but it is incremental as it builds on existing methods with specific architectural tweaks.
The paper tackled dialog act classification by exploring neural-based context representation learning, comparing recurrent neural networks with attention mechanisms at different context levels, and achieved consistent improvements over non-contextual models on two benchmark datasets.
We explore context representation learning methods in neural-based models for dialog act classification. We propose and compare extensively different methods which combine recurrent neural network architectures and attention mechanisms (AMs) at different context levels. Our experimental results on two benchmark datasets show consistent improvements compared to the models without contextual information and reveal that the most suitable AM in the architecture depends on the nature of the dataset.