A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation
This work addresses the challenge of improving language generation for conversational agents, but it appears incremental as it builds on existing ensemble and data augmentation techniques without a major paradigm shift.
The paper tackled the problem of natural language generation for dialogue systems by introducing an ensemble neural model with novel data representation and augmentation methods, achieving better results than state-of-the-art models on three datasets in restaurant, TV, and laptop domains as shown by both automatic metrics and human evaluations.
Natural language generation lies at the core of generative dialogue systems and conversational agents. We describe an ensemble neural language generator, and present several novel methods for data representation and augmentation that yield improved results in our model. We test the model on three datasets in the restaurant, TV and laptop domains, and report both objective and subjective evaluations of our best model. Using a range of automatic metrics, as well as human evaluators, we show that our approach achieves better results than state-of-the-art models on the same datasets.