# A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsing

arXiv: https://arxiv.org/abs/2210.08355 · HTML: https://mlsanity.com/paper/2210.08355/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 15 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Discourse-Aware Neural Extractive Text Summarization](https://mlsanity.com/paper/1910.14142/) (2019)
- [Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading](https://mlsanity.com/paper/2010.01838/) (2020)
- [Better Document-level Sentiment Analysis from RST Discourse Parsing](https://mlsanity.com/paper/1509.01599/) (2015)
- [A Unified Linear-Time Framework for Sentence-Level Discourse Parsing](https://mlsanity.com/paper/1905.05682/) (2019)
- [RST Parsing from Scratch](https://mlsanity.com/paper/2105.10861/) (2021)
- [Stronger Baselines for Trustable Results in Neural Machine Translation](https://mlsanity.com/paper/1706.09733/) (2017)
- [A Top-Down Neural Architecture towards Text-Level Parsing of Discourse Rhetorical Structure](https://mlsanity.com/paper/2005.02680/) (2020)
- [Top-down Discourse Parsing via Sequence Labelling](https://mlsanity.com/paper/2102.02080/) (2021)
- [Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining](https://mlsanity.com/paper/2011.03203/) (2020)
- [Fast Rhetorical Structure Theory Discourse Parsing](https://mlsanity.com/paper/1505.02425/) (2015)
- [An End-to-End Document-Level Neural Discourse Parser Exploiting Multi-Granularity Representations](https://mlsanity.com/paper/2012.11169/) (2020)
- [Strong and Simple Baselines for Multimodal Utterance Embeddings](https://mlsanity.com/paper/1906.02125/) (2019)

## Built on by (most cited first, 5 of 5)

- [eRST: A Signaled Graph Theory of Discourse Relations and Organization](https://mlsanity.com/paper/2403.13560/) (2024)
- [Bilingual Rhetorical Structure Parsing with Large Parallel Annotations](https://mlsanity.com/paper/2409.14969/) (2024)
- [Can we obtain significant success in RST discourse parsing by using Large Language Models?](https://mlsanity.com/paper/2403.05065/) (2024)
- [Topic-driven Distant Supervision Framework for Macro-level Discourse Parsing](https://mlsanity.com/paper/2305.13755/) (2023)
- [Worth Their Weights? Evaluating Generative Models for Discourse Parsing](https://mlsanity.com/paper/2610.17658/) (2026)

## Abstract (arXiv)

To promote and further develop RST-style discourse parsing models, we need a strong baseline that can be regarded as a reference for reporting reliable experimental results. This paper explores a strong baseline by integrating existing simple parsing strategies, top-down and bottom-up, with various transformer-based pre-trained language models. The experimental results obtained from two benchmark datasets demonstrate that the parsing performance strongly relies on the pretrained language models rather than the parsing strategies. In particular, the bottom-up parser achieves large performance gains compared to the current best parser when employing DeBERTa. We further reveal that language models with a span-masking scheme especially boost the parsing performance through our analysis within intra- and multi-sentential parsing, and nuclearity prediction.