mlsanityData to 7 Oct 2026

eRST: A Signaled Graph Theory of Discourse Relations and Organization

arXiv 2403.13560 ↗First posted 20 Mar 2024cs.CLcited by 13

Not on the map. Why?

Abstract (arXiv)

In this article we present Enhanced Rhetorical Structure Theory (eRST), a new theoretical framework for computational discourse analysis, based on an expansion of Rhetorical Structure Theory (RST). The framework encompasses discourse relation graphs with tree-breaking, non-projective and concurrent relations, as well as implicit and explicit signals which give explainable rationales to our analyses. We survey shortcomings of RST and other existing frameworks, such as Segmented Discourse Representation Theory (SDRT), the Penn Discourse Treebank (PDTB) and Discourse Dependencies, and address these using constructs in the proposed theory. We provide annotation, search and visualization tools for data, and present and evaluate a freely available corpus of English annotated according to our framework, encompassing 12 spoken and written genres with over 200K tokens. Finally, we discuss automatic parsing, evaluation metrics and applications for data in our framework.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 24 of its 128 references that are in the map. First posted on arXiv 20 Mar 2024.

Builds on

24 of 128 references.

References · 24

  1. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  2. 2020Universal Dependencies v2: An Evergrowing Multilingual Treebank Collectioncited by 269
  3. 2020Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structurecited by 60
  4. 2021DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and Parsingcited by 27
  5. 2018SciDTB: Discourse Dependency TreeBank for Scientific Abstractscited by 24
  6. 2023DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognitioncited by 23
  7. 2017Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classificationcited by 17
  8. 2018Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraphcited by 17
  9. 2023Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarizationcited by 17
  10. 2023GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic Evaluationcited by 17
  11. 2021DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective Detectioncited by 15
  12. 2022GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsingcited by 13
12 more
  1. 2021Probing Multilingual Language Models for Discoursecited by 12
  2. 2019All Roads Lead to UD: Converting Stanford and Penn Parses to English Universal Dependencies with Multilayer Annotationscited by 9
  3. 2020AMALGUM -- A Free, Balanced, Multilayer English Web Corpuscited by 9
  4. 2021Unifying Discourse Resources with Dependency Frameworkcited by 8
  5. 2023Quality and Efficiency of Manual Annotation: Pre-annotation Biascited by 8
  6. 2022Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language Modelscited by 6
  7. 2019Zero-shot Chinese Discourse Dependency Parsing via Cross-lingual Mappingcited by 5
  8. 2020Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretrainingcited by 5
  9. 2022Improving Topic Segmentation by Injecting Discourse Dependenciescited by 5
  10. 2019Beyond The Wall Street Journal: Anchoring and Comparing Discourse Signals across Genrescited by 4
  11. 2022A Simple and Strong Baseline for End-to-End Neural RST-style Discourse Parsingcited by 4
  12. 2023What's Hard in English RST Parsing? Predictive Models for Error Analysiscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 4.

13 papers.

Sort:

By area:

  1. 2024GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domainscited by 5
  2. 2025Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Setcited by 4
  3. 2025Discursive Circuits: How Do Language Models Understand Discourse Relations?cited by 3
  4. 2025DeDisCo at the DISRPT 2025 Shared Task: A System for Discourse Relation Classificationcited by 1
  5. 2026Disco-RAG: Discourse-Aware Retrieval-Augmented Generationcited by 1
  6. 2025Rethinking the Relationship between the Power Law and Hierarchical Structurescited by 0
  7. 2025LLMSR@XLLM25: An Empirical Study of LLM for Structural Reasoningcited by 0
  8. 2025Unpacking Ambiguity: The Interaction of Polysemous Discourse Markers and Non-DM Signalscited by 0
  9. 2025What makes an entity salient in discourse?cited by 0
  10. 2025Bridging Discourse Treebanks with a Unified Rhetorical Structure Parsercited by 0
  11. 2026Human Label Variation in Implicit Discourse Relation Recognitioncited by 0
  12. 2026DiscoExplorer: An Open Interface for the Study of Multilingual Discourse Relationscited by 0
1 more
  1. 2026Using LMs to Model the Effects of Context and Coreference during Sentence Comprehensioncited by 0