A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation

TL;DR

This paper introduces a deep ensemble neural language generation model with slot alignment, employing novel data representation and augmentation techniques, achieving superior results in dialogue domain datasets through both automatic and human evaluations.

Contribution

The paper presents a novel ensemble model with slot alignment and new data augmentation methods for improved sequence-to-sequence natural language generation.

Findings

Outperforms state-of-the-art models on multiple datasets

Achieves higher scores in automatic evaluation metrics

Receives positive subjective evaluations from human judges

Abstract

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.