Polite Dialogue Generation Without Parallel Data
arXiv:1805.03162
Abstract
Stylistic dialogue response generation, with valuable applications in personality-based conversational agents, is a challenging task because the response needs to be fluent, contextually-relevant, as well as paralinguistically accurate. Moreover, parallel datasets for regular-to-stylistic pairs are usually unavailable. We present three weakly-supervised models that can generate diverse polite (or rude) dialogue responses without parallel data. Our late fusion model (Fusion) merges the decoder of an encoder-attention-decoder dialogue model with a language model trained on stand-alone polite utterances. Our label-fine-tuning (LFT) model prepends to each source sequence a politeness-score scaled label (predicted by our state-of-the-art politeness classifier) during training, and at test time is able to generate polite, neutral, and rude responses by simply scaling the label embedding by the corresponding score. Our reinforcement learning model (Polite-RL) encourages politeness generation by assigning rewards proportional to the politeness classifier score of the sampled response. We also present two retrieval-based polite dialogue model baselines. Human evaluation validates that while the Fusion and the retrieval-based models achieve politeness with poorer context-relevance, the LFT and Polite-RL models can produce significantly more polite responses without sacrificing dialogue quality.
arXiv commentTo Appear in TACL Journal (16 pages) (first submission cycle: Oct1 2017)
References in corpus (16)
- Efficient Estimation of Word Representations in Vector Space
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- A Deep Reinforced Model for Abstractive Summarization
- Exploring the Limits of Language Modeling
- A C-LSTM Neural Network for Text Classification
- Style Transfer from Non-Parallel Text by Cross-Alignment
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Unsupervised Image-to-Image Translation Networks
- Unsupervised Cross-Domain Image Generation
- A Persona-Based Neural Conversation Model
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- A Computational Approach to Politeness with Application to Social Factors
- deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
- Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models
- Controlling Output Length in Neural Encoder-Decoders
- Steering Output Style and Topic in Neural Response Generation