Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

Abstract

We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare two-step generation with separate sentence planning and surface realization stages to a joint, one-step approach. We were able to train both setups successfully using very little training data.

The joint setup offers better performance, surpassing state-of-the-art with regards to n-gram-based scores while providing more relevant outputs.

Keywords

• sequence
• sequence
• generation
• spoken
• dialogue
• deep
• syntax
• trees
• strings