# Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems

arXiv: https://arxiv.org/abs/2005.12529 · HTML: https://mlsanity.com/paper/2005.12529/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2020.

## Built on by (most cited first, 17 of 17)

- [Multi-Stage Prompting for Knowledgeable Dialogue Generation](https://mlsanity.com/paper/2203.08745/) (2022)
- [Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers](https://mlsanity.com/paper/2108.00308/) (2021)
- [Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation](https://mlsanity.com/paper/2205.09314/) (2022)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [CASPR: A Commonsense Reasoning-based Conversational Socialbot](https://mlsanity.com/paper/2110.05387/) (2021)
- [Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue](https://mlsanity.com/paper/2110.08094/) (2021)
- [Zero-Shot Controlled Generation with Encoder-Decoder Transformers](https://mlsanity.com/paper/2106.06411/) (2021)
- [Proto: A Neural Cocktail for Generating Appealing Conversations](https://mlsanity.com/paper/2109.02513/) (2021)
- [Modeling Performance in Open-Domain Dialogue with PARADISE](https://mlsanity.com/paper/2110.11164/) (2021)
- [A Systematic Evaluation of Response Selection for Open Domain Dialogue](https://mlsanity.com/paper/2208.04379/) (2022)
- [Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking](https://mlsanity.com/paper/2307.14440/) (2023)
- [Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues](https://mlsanity.com/paper/2106.03065/) (2021)
- [Viola: A Topic Agnostic Generate-and-Rank Dialogue System](https://mlsanity.com/paper/2108.11063/) (2021)
- [DiscASP: A Graph-based ASP System for Finding Relevant Consistent Concepts with Applications to Conversational Socialbots](https://mlsanity.com/paper/2109.08297/) (2021)
- [Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey](https://mlsanity.com/paper/2411.09166/) (2024)
- [Use of a Taxonomy of Empathetic Response Intents to Control and Interpret Empathy in Neural Chatbots](https://mlsanity.com/paper/2305.10096/) (2023)
- [Athena 2.0: Discourse and User Modeling in Open Domain Dialogue](https://mlsanity.com/paper/2308.01887/) (2023)

## Abstract (arXiv)

Open-domain dialogue systems aim to generate relevant, informative and engaging responses. Seq2seq neural response generation approaches do not have explicit mechanisms to control the content or style of the generated response, and frequently result in uninformative utterances. In this paper, we propose using a dialogue policy to plan the content and style of target responses in the form of an action plan, which includes knowledge sentences related to the dialogue context, targeted dialogue acts, topic information, etc. The attributes within the action plan are obtained by automatically annotating the publicly released Topical-Chat dataset. We condition neural response generators on the action plan which is then realized as target utterances at the turn and sentence levels. We also investigate different dialogue policy models to predict an action plan given the dialogue context. Through automated and human evaluation, we measure the appropriateness of the generated responses and check if the generation models indeed learn to realize the given action plans. We demonstrate that a basic dialogue policy that operates at the sentence level generates better responses in comparison to turn level generation as well as baseline models with no action plan. Additionally the basic dialogue policy has the added effect of controllability.