RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators
Not on the map. Why?
Abstract (arXiv)
In this paper, we study the task of improving the cohesion and coherence of long-form text generated by language models. To this end, we propose RSTGen, a framework that utilises Rhetorical Structure Theory (RST), a classical language theory, to control the discourse structure, semantics and topics of generated text. Firstly, we demonstrate our model's ability to control structural discourse and semantic features of generated text in open generation evaluation. Then we experiment on the two challenging long-form text tasks of argument generation and story generation. Evaluation using automated metrics and a metric with high correlation to human evaluation, shows that our model performs competitively against existing models, while offering significantly more controls over generated text than alternative methods.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 25 May 2022.
Builds on
30 of 42 references.
References · 30
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2018Hierarchical Neural Story Generationcited by 1,193
- 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
- 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
- 2017Toward Controlled Generation of Textcited by 272
- 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 234
- 2017Challenges in Data-to-Document Generationcited by 226
- 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
- 2019Strategies for Structuring Story Generationcited by 124
- 2018Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networkscited by 101
- 2019Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generationcited by 75
18 more
- 2020ConvoKit: A Toolkit for the Analysis of Conversationscited by 72
- 2019Tree Transformer: Integrating Tree Structures into Self-Attentioncited by 68
- 2019Jointly Measuring Diversity and Quality in Text Generation Modelscited by 61
- 2020Neural Syntactic Preordering for Controlled Paraphrase Generationcited by 56
- 2019Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Modelscited by 53
- 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
- 2019A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representationscited by 37
- 2020GRUEN for Evaluating Linguistic Quality of Generated Textcited by 37
- 2019Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialoguecited by 35
- 2020PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generationcited by 35
- 2020Tree-structured Attention with Hierarchical Accumulationcited by 30
- 2016Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Stringscited by 27
- 2019Sentence-Level Content Planning and Style Specification for Neural Text Generationcited by 23
- 2018Toward Fast and Accurate Neural Discourse Segmentationcited by 19
- 2021DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformercited by 14
- 2021DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generationcited by 11
- 2020Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approachcited by 8
- 2020Transformer-Based Neural Text Generation with Syntactic Guidancecited by 5
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 1.
3 papers.