Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
arXiv:1710.07388
Abstract
Building a persona-based conversation agent is challenging owing to the lack of large amounts of speaker-specific conversation data for model training. This paper addresses the problem by proposing a multi-task learning approach to training neural conversation models that leverages both conversation data across speakers and other types of data pertaining to the speaker and speaker roles to be modeled. Experiments show that our approach leads to significant improvements over baseline model quality, generating responses that capture more precisely speakers' traits and speaking styles. The model offers the benefits of being algorithmically simple and easy to implement, and not relying on large quantities of data representing specific individual speakers.
References in corpus (8)
- A Neural Conversational Model
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- A Persona-Based Neural Conversation Model
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
- deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
- LSTM based Conversation Models
- Coherent Dialogue with Attention-based Language Models
- Scientific Information Extraction with Semi-supervised Neural Tagging
Cited by in corpus (15)
- Meta-evaluation of Conversational Search Evaluation Metrics
- Challenges in Building Intelligent Open-domain Dialog Systems
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
- OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
- Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function
- Structuring Latent Spaces for Stylized Response Generation
- Conditional Text Generation for Harmonious Human-Machine Interaction
- Polite Dialogue Generation Without Parallel Data
- Learning Personalized End-to-End Goal-Oriented Dialog
- Personalized Multimodal Feedback Generation in Education
- Monolingual sentence matching for text simplification
- A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation
- Automatic Evaluation of Neural Personality-based Chatbots
- Scientific Relation Extraction with Selectively Incorporated Concept Embeddings
- AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions