A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions

TL;DR

This survey reviews the evolution of natural language generation, especially dialogue systems, highlighting traditional, statistical, and neural approaches, and discusses future research directions to improve system coherence, context understanding, and personalization.

Contribution

It provides a comprehensive overview of NLG techniques with a focus on dialogue systems, identifying key challenges and proposing future research directions involving cognitive architectures.

Findings

Most dialogue systems use seq2seq or language models.

Key research areas include context integration, personality, and response quality.

Open problems include handling context, personality, and avoiding generic responses.

Abstract

One of the hardest problems in the area of Natural Language Processing and Artificial Intelligence is automatically generating language that is coherent and understandable to humans. Teaching machines how to converse as humans do falls under the broad umbrella of Natural Language Generation. Recent years have seen unprecedented growth in the number of research articles published on this subject in conferences and journals both by academic and industry researchers. There have also been several workshops organized alongside top-tier NLP conferences dedicated specifically to this problem. All this activity makes it hard to clearly define the state of the field and reason about its future directions. In this work, we provide an overview of this important and thriving area, covering traditional approaches, statistical approaches and also approaches that use deep neural networks. We provide a comprehensive review towards building open domain dialogue systems, an important application of natural language generation. We find that, predominantly, the approaches for building dialogue systems use seq2seq or language models architecture. Notably, we identify three important areas of further research towards building more effective dialogue systems: 1) incorporating larger context, including conversation context and world knowledge; 2) adding personae or personality in the NLG system; and 3) overcoming dull and generic responses that affect the quality of system-produced responses. We provide pointers on how to tackle these open problems through the use of cognitive architectures that mimic human language understanding and generation capabilities.