# RST Parsing from Scratch

arXiv: https://arxiv.org/abs/2105.10861 · HTML: https://mlsanity.com/paper/2105.10861/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 23 May 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [A Minimal Span-Based Neural Constituency Parser](https://mlsanity.com/paper/1705.03919/) (2017)
- [Stack-Pointer Networks for Dependency Parsing](https://mlsanity.com/paper/1805.01087/) (2018)
- [Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading](https://mlsanity.com/paper/2010.01838/) (2020)
- [Neural Discourse Structure for Text Categorization](https://mlsanity.com/paper/1702.01829/) (2017)
- [Better Document-level Sentiment Analysis from RST Discourse Parsing](https://mlsanity.com/paper/1509.01599/) (2015)
- [Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles](https://mlsanity.com/paper/1612.06475/) (2016)
- [Cross-lingual RST Discourse Parsing](https://mlsanity.com/paper/1701.02946/) (2017)
- [A Unified Linear-Time Framework for Sentence-Level Discourse Parsing](https://mlsanity.com/paper/1905.05682/) (2019)
- [A Top-Down Neural Architecture towards Text-Level Parsing of Discourse Rhetorical Structure](https://mlsanity.com/paper/2005.02680/) (2020)
- [Discourse Structure in Machine Translation Evaluation](https://mlsanity.com/paper/1710.01504/) (2017)

## Built on by (most cited first, 14 of 14)

- [DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsing](https://mlsanity.com/paper/2110.04518/) (2021)
- [Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks](https://mlsanity.com/paper/2110.05419/) (2021)
- [Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization](https://mlsanity.com/paper/2305.16784/) (2023)
- [DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detection](https://mlsanity.com/paper/2109.09777/) (2021)
- [Why Can't Discourse Parsing Generalize? A Thorough Investigation of the Impact of Data Diversity](https://mlsanity.com/paper/2302.06488/) (2023)
- [Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Models](https://mlsanity.com/paper/2204.04289/) (2022)
- [Bilingual Rhetorical Structure Parsing with Large Parallel Annotations](https://mlsanity.com/paper/2409.14969/) (2024)
- [A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing](https://mlsanity.com/paper/2210.08355/) (2022)
- [Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues](https://mlsanity.com/paper/2302.05895/) (2023)
- [Can we obtain significant success in RST discourse parsing by using Large Language Models?](https://mlsanity.com/paper/2403.05065/) (2024)
- [Bridging Discourse Treebanks with a Unified Rhetorical Structure Parser](https://mlsanity.com/paper/2510.06427/) (2025)
- [What's Hard in English RST Parsing? Predictive Models for Error Analysis](https://mlsanity.com/paper/2309.04940/) (2023)
- [RST-style Discourse Parsing Guided by Document-level Content Structures](https://mlsanity.com/paper/2309.04141/) (2023)
- [Worth Their Weights? Evaluating Generative Models for Discourse Parsing](https://mlsanity.com/paper/2610.17658/) (2026)

## Abstract (arXiv)

We introduce a novel top-down end-to-end formulation of document-level discourse parsing in the Rhetorical Structure Theory (RST) framework. In this formulation, we consider discourse parsing as a sequence of splitting decisions at token boundaries and use a seq2seq network to model the splitting decisions. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite; rather, it yields segmentation as part of the parsing process. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high-scoring trees. With extensive experiments on the standard English RST discourse treebank, we demonstrate that our parser outperforms existing methods by a good margin in both end-to-end parsing and parsing with gold segmentation. More importantly, it does so without using any handcrafted features, making it faster and easily adaptable to new languages and domains.