Controlling Style in Generated Dialogue

Abstract

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training data required to train these architectures aggregates many different styles, tones, and qualities. Using that data to train a single model makes it difficult to use the model as a consistent conversational agent, e.g. with a stable set of persona traits and a typical style of expression. Several architectures affording control mechanisms over generation architectures have been proposed, each with different trade-offs. However, it remains unclear whether their use in dialogue is viable, and what the trade-offs look like with the most recent state-of-the-art conversational architectures. In this work, we adapt three previously proposed controllable generation architectures to open-domain dialogue generation, controlling the style of the generation to match one among about 200 possible styles. We compare their respective performance and tradeoffs, and show how they can be used to provide insights into existing conversational datasets, and generate a varied set of styled conversation replies.

References in corpus (8)

• Language Models are Few-Shot Learners
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• Towards a Human-like Open-Domain Chatbot
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer
• Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles

Cited by in corpus (8)

• Recipes for Safety in Open-domain Chatbots
• Few-Shot Bot: Prompt-Based Learning for Dialogue Systems
• Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence
• Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models
• Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning
• What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers
• Zero-Shot Controlled Generation with Encoder-Decoder Transformers
• Attribute Alignment: Controlling Text Generation from Pre-trained Language Models