# Polite Dialogue Generation Without Parallel Data

arXiv: https://arxiv.org/abs/1805.03162 · HTML: https://mlsanity.com/paper/1805.03162/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2018.

## Built on by (most cited first, 30 of 59)

- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support](https://mlsanity.com/paper/2106.01702/) (2021)
- [Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features](https://mlsanity.com/paper/2107.06963/) (2021)
- [Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts](https://mlsanity.com/paper/2108.11830/) (2021)
- [Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance](https://mlsanity.com/paper/2402.08680/) (2024)
- [Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems](https://mlsanity.com/paper/2310.05280/) (2023)
- [Elastic Weight Removal for Faithful and Abstractive Dialogue Generation](https://mlsanity.com/paper/2303.17574/) (2023)
- [Focused Attention Improves Document-Grounded Generation](https://mlsanity.com/paper/2104.12714/) (2021)
- [Stylized Story Generation with Style-Guided Planning](https://mlsanity.com/paper/2105.08625/) (2021)
- [TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages](https://mlsanity.com/paper/2211.16496/) (2022)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Parameter-Efficient Detoxification with Contrastive Decoding](https://mlsanity.com/paper/2401.06947/) (2024)
- [Controllable Summarization with Constrained Markov Decision Process](https://mlsanity.com/paper/2108.03405/) (2021)
- [C5T5: Controllable Generation of Organic Molecules with Transformers](https://mlsanity.com/paper/2108.10307/) (2021)
- [Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation](https://mlsanity.com/paper/2204.10703/) (2022)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Inference Time Style Control for Summarization](https://mlsanity.com/paper/2104.01724/) (2021)
- [Text Style Transfer Evaluation Using Large Language Models](https://mlsanity.com/paper/2308.13577/) (2023)
- [Transductive Learning for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2109.07812/) (2021)
- [MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control](https://mlsanity.com/paper/2310.18342/) (2023)
- [DetoxLLM: A Framework for Detoxification with Explanations](https://mlsanity.com/paper/2402.15951/) (2024)
- [MOPO: Multi-Objective Prompt Optimization for Affective Text Generation](https://mlsanity.com/paper/2412.12948/) (2024)
- [Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation](https://mlsanity.com/paper/2205.09314/) (2022)
- [StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing](https://mlsanity.com/paper/2208.13423/) (2022)
- [Computational Politeness in Natural Language Processing: A Survey](https://mlsanity.com/paper/2407.12814/) (2024)
- [Changing the Mind of Transformers for Topically-Controllable Language Generation](https://mlsanity.com/paper/2103.15335/) (2021)
- [CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning](https://mlsanity.com/paper/2110.03949/) (2021)
- [Advancements in Scientific Controllable Text Generation Methods](https://mlsanity.com/paper/2307.05538/) (2023)

## Abstract (arXiv)

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.