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.

Accepted as a short paper for ACL 2016

Cited by in corpus (6)

• A Survey on Dialogue Systems: Recent Advances and New Frontiers
• When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
• Survey on Evaluation Methods for Dialogue Systems
• Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
• GenNI: Human-AI Collaboration for Data-Backed Text Generation
• Copy mechanism and tailored training for character-based data-to-text generation