# Neural Discourse Structure for Text Categorization

arXiv: https://arxiv.org/abs/1702.01829 · HTML: https://mlsanity.com/paper/1702.01829/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2017.

## Built on by (most cited first, 24 of 24)

- [RST Parsing from Scratch](https://mlsanity.com/paper/2105.10861/) (2021)
- [Conflicts, Villains, Resolutions: Towards models of Narrative Media Framing](https://mlsanity.com/paper/2306.02052/) (2023)
- [Discourse Analysis via Questions and Answers: Parsing Dependency Structures of Questions Under Discussion](https://mlsanity.com/paper/2210.05905/) (2022)
- [Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions](https://mlsanity.com/paper/2402.13551/) (2024)
- [Us vs. Them: A Dataset of Populist Attitudes, News Bias and Emotions](https://mlsanity.com/paper/2101.11956/) (2021)
- [Evaluating Document Coherence Modelling](https://mlsanity.com/paper/2103.10133/) (2021)
- [Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media Frames](https://mlsanity.com/paper/2104.11030/) (2021)
- [Discourse Relation Embeddings: Representing the Relations between Discourse Segments in Social Media](https://mlsanity.com/paper/2105.01306/) (2021)
- [Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models](https://mlsanity.com/paper/2204.04289/) (2022)
- [Understanding Social Media Cross-Modality Discourse in Linguistic Space](https://mlsanity.com/paper/2302.13311/) (2023)
- [Connecting the Dots in News Analysis: Bridging the Cross-Disciplinary Disparities in Media Bias and Framing](https://mlsanity.com/paper/2309.08069/) (2023)
- [Predicting Above-Sentence Discourse Structure using Distant Supervision from Topic Segmentation](https://mlsanity.com/paper/2112.06196/) (2021)
- [Structured Dialogue Discourse Parsing](https://mlsanity.com/paper/2306.15103/) (2023)
- [Talking Point based Ideological Discourse Analysis in News Events](https://mlsanity.com/paper/2504.07400/) (2025)
- [Retain or Reframe? A Computational Framework for the Analysis of Framing in News Articles and Reader Comments](https://mlsanity.com/paper/2507.04612/) (2025)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)
- [Linguistic-style-aware Neural Networks for Fake News Detection](https://mlsanity.com/paper/2301.02792/) (2023)
- [W-RST: Towards a Weighted RST-style Discourse Framework](https://mlsanity.com/paper/2106.02658/) (2021)
- [Towards Corpus-Scale Discovery of Selection Biases in News Coverage: Comparing What Sources Say About Entities as a Start](https://mlsanity.com/paper/2304.03414/) (2023)
- [A Structured Clustering Approach for Inducing Media Narratives](https://mlsanity.com/paper/2604.10368/) (2026)
- [Biaffine Discourse Dependency Parsing](https://mlsanity.com/paper/2201.04450/) (2022)
- [Unsupervised Inference of Data-Driven Discourse Structures using a Tree Auto-Encoder](https://mlsanity.com/paper/2210.09559/) (2022)
- [Towards Domain-Independent Supervised Discourse Parsing Through Gradient Boosting](https://mlsanity.com/paper/2210.09565/) (2022)
- [Large Discourse Treebanks from Scalable Distant Supervision](https://mlsanity.com/paper/2212.06038/) (2022)

## Abstract (arXiv)

We show that discourse structure, as defined by Rhetorical Structure Theory and provided by an existing discourse parser, benefits text categorization. Our approach uses a recursive neural network and a newly proposed attention mechanism to compute a representation of the text that focuses on salient content, from the perspective of both RST and the task. Experiments consider variants of the approach and illustrate its strengths and weaknesses.