# Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memory

arXiv: https://arxiv.org/abs/2004.02214 · HTML: https://mlsanity.com/paper/2004.02214/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2020.

## Built on by (most cited first, 22 of 22)

- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Language Models Can See: Plugging Visual Controls in Text Generation](https://mlsanity.com/paper/2205.02655/) (2022)
- [Contrastive Search Is What You Need For Neural Text Generation](https://mlsanity.com/paper/2210.14140/) (2022)
- [ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning](https://mlsanity.com/paper/2306.06466/) (2023)
- [TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning](https://mlsanity.com/paper/2111.04198/) (2021)
- [Few-Shot Table-to-Text Generation with Prototype Memory](https://mlsanity.com/paper/2108.12516/) (2021)
- [An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text Generation](https://mlsanity.com/paper/2211.10797/) (2022)
- [Transductive Learning for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2109.07812/) (2021)
- [GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation](https://mlsanity.com/paper/2508.20757/) (2025)
- [SuperRAG: Beyond RAG with Layout-Aware Graph Modeling](https://mlsanity.com/paper/2503.04790/) (2025)
- [Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting](https://mlsanity.com/paper/2204.05610/) (2022)
- [Momentum Decoding: Open-ended Text Generation As Graph Exploration](https://mlsanity.com/paper/2212.02175/) (2022)
- [Incorporating Task-specific Concept Knowledge into Script Learning](https://mlsanity.com/paper/2209.00068/) (2022)
- [Stylistic Retrieval-based Dialogue System with Unparallel Training Data](https://mlsanity.com/paper/2109.05477/) (2021)
- [Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning](https://mlsanity.com/paper/2402.12177/) (2024)
- [Prompt Guided Copy Mechanism for Conversational Question Answering](https://mlsanity.com/paper/2308.03422/) (2023)
- [Fine-grained Conversational Decoding via Isotropic and Proximal Search](https://mlsanity.com/paper/2310.08130/) (2023)
- [QASE Enhanced PLMs: Improved Control in Text Generation for MRC](https://mlsanity.com/paper/2403.04771/) (2024)
- [Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension](https://mlsanity.com/paper/2404.17991/) (2024)
- [A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation](https://mlsanity.com/paper/2410.20174/) (2024)

## Abstract (arXiv)

The ability of a dialog system to express prespecified language style during conversations has a direct, positive impact on its usability and on user satisfaction. We introduce a new prototype-to-style (PS) framework to tackle the challenge of stylistic dialogue generation. The framework uses an Information Retrieval (IR) system and extracts a response prototype from the retrieved response. A stylistic response generator then takes the prototype and the desired language style as model input to obtain a high-quality and stylistic response. To effectively train the proposed model, we propose a new style-aware learning objective as well as a de-noising learning strategy. Results on three benchmark datasets from two languages demonstrate that the proposed approach significantly outperforms existing baselines in both in-domain and cross-domain evaluations