# Discourse-Aware Neural Rewards for Coherent Text Generation

arXiv: https://arxiv.org/abs/1805.03766 · HTML: https://mlsanity.com/paper/1805.03766/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2018.

## Built on by (most cited first, 28 of 28)

- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation](https://mlsanity.com/paper/2203.05386/) (2022)
- [ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations](https://mlsanity.com/paper/2304.14827/) (2023)
- [PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation](https://mlsanity.com/paper/2203.09100/) (2022)
- [DAGN: Discourse-Aware Graph Network for Logical Reasoning](https://mlsanity.com/paper/2103.14349/) (2021)
- [APPDIA: A Discourse-aware Transformer-based Style Transfer Model for Offensive Social Media Conversations](https://mlsanity.com/paper/2209.08207/) (2022)
- [DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2305.03973/) (2023)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts](https://mlsanity.com/paper/2109.12761/) (2021)
- [DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer](https://mlsanity.com/paper/2110.05999/) (2021)
- [DisCGen: A Framework for Discourse-Informed Counterspeech Generation](https://mlsanity.com/paper/2311.18147/) (2023)
- [Self-Consistent Narrative Prompts on Abductive Natural Language Inference](https://mlsanity.com/paper/2309.08303/) (2023)
- [RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization](https://mlsanity.com/paper/2405.00657/) (2024)
- [Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions](https://mlsanity.com/paper/2106.03158/) (2021)
- [Coherence-Driven Multimodal Safety Dialogue with Active Learning for Embodied Agents](https://mlsanity.com/paper/2410.14141/) (2024)
- [AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys](https://mlsanity.com/paper/2510.26012/) (2025)
- [Learning from Executions for Semantic Parsing](https://mlsanity.com/paper/2104.05819/) (2021)
- [Exploring Discourse Structures for Argument Impact Classification](https://mlsanity.com/paper/2106.00976/) (2021)
- [Hallmarks of Human-Machine Collaboration: A framework for assessment in the DARPA Communicating with Computers Program](https://mlsanity.com/paper/2102.04958/) (2021)
- [Sequentially Controlled Text Generation](https://mlsanity.com/paper/2301.02299/) (2023)
- [Using BERT Encoding and Sentence-Level Language Model for Sentence Ordering](https://mlsanity.com/paper/2108.10986/) (2021)
- [Ratatouille: A tool for Novel Recipe Generation](https://mlsanity.com/paper/2206.08267/) (2022)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)
- [Recipe Generation from Unsegmented Cooking Videos](https://mlsanity.com/paper/2209.10134/) (2022)
- [Plot Writing From Pre-Trained Language Models](https://mlsanity.com/paper/2206.03021/) (2022)
- [Instruct-SCTG: Guiding Sequential Controlled Text Generation through Instructions](https://mlsanity.com/paper/2312.12299/) (2023)
- [Fine-Grained Evaluation for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2503.05326/) (2025)

## Abstract (arXiv)

In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired discourse structure. Empirical results demonstrate that a generator trained with the learned reward produces more coherent and less repetitive text than models trained with cross-entropy or with reinforcement learning with commonly used scores as rewards.