Papers with RST
Using and comparing Rhetorical Structure Theory parsers with rst-workbench (2021.eacl-demos)
Copied to clipboard
| Challenge: | Rhetorical Structure Theory (RST) parsers are usually only trained on English data . |
| Approach: | rst-workbench is a web-based tool that lets users install and use RST parsers. |
| Outcome: | rst-workbench is a web-based tool that lets users run multiple RST parsers simultaneously. |
Towards Unification of Discourse Annotation Frameworks (2022.acl-srw)
Copied to clipboard
| Challenge: | Discourse information is difficult to represent and annotate, and corpora annotated under different frameworks vary considerably. |
| Approach: | They propose to use automatic means to unify discourse structures and relations . they will also explore the application of the unified framework in multi-task learning and graphical models . |
| Outcome: | The proposed method can be used in multi-task learning and graphical models. |
GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing (2022.aacl-short)
Copied to clipboard
| Challenge: | GCDT is the largest hierarchical discourse treebank for Mandarin Chinese in the framework of Rhetorical Structure Theory (RST). |
| Approach: | They propose to use a Chinese hierarchical discourse treebank to parse Mandarin Chinese using relation inventory and a multilingual training program. |
| Outcome: | The proposed dataset includes state-of-the-art scores for Chinese RST parsing and RST Parsing on the English GUM dataset, using cross-lingual training in Chinese and English with multilingual embeddings. |
Extractive Summarisation for German-language Data: A Text-level Approach with Discourse Features (2022.coling-1)
Copied to clipboard
| Challenge: | Using RST, extractive summarisation involves using select phrases and sentences as a summary, which still remains a strong method for producing summaries despite its simple nature. |
| Approach: | They propose to use RST-based features to analyse the connection between summary sentences and several RST features and transfer these insights to various automated summarisation models. |
| Outcome: | The proposed models are based on the best features proposed over the last 20+ years and incorporate the best ones into the proposed models. |
Neural RST-based Evaluation of Discourse Coherence (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing discourse parsers cannot predict coherent texts without using silver-standard features. |
| Approach: | They propose a tree-recursive neural model which takes advantage of the text’s RST features produced by a state of the art RST parser and compares it to the current state of art. |
| Outcome: | The proposed model achieves state-of-the-art accuracy on the Grammarly Corpus for Discourse Coherence (GCDC) and has 62% fewer parameters than existing models. |
A Survey of QUD Models for Discourse Processing (2025.naacl-long)
Copied to clipboard
| Challenge: | Question Under Discussion (QUD) is a linguistic analytic framework for explaining pragmatic phenomena and information structural analysis. |
| Approach: | They propose to use Question Under Discussion (QUD) to model discourse units, such as sentences, as answers to some implicit or explicit questions. |
| Outcome: | The proposed model is compared with RST, PDTB and SDRT . questions that may require further study are suggested. |
RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to integrate rhetorical structure theory into long document summarization models are unexplored. |
| Approach: | They propose to integrate rhetorical structure theory into a long document summarization model by explicitly incorporating rhetorical uncertainty into the model. |
| Outcome: | The proposed models outperform the vanilla LoRA and full-parameter fine-tuning models and outperformed previous state-of-the-art methods. |
Improving Neural RST Parsing Model with Silver Agreement Subtrees (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for Rhetorical Structure Theory (RST) parsing use supervised learning, but the RST-DT is small due to the costly annotation of RST trees. |
| Approach: | They propose to use silver data to improve RST parsing models by using annotated silver data. |
| Outcome: | The proposed method achieves the best micro-F1 scores for Nuclearity and Relation at 75.0 and 63.2 . it also achieves a remarkable gain in relation score against the previous state-of-the-art parser. |
RST Parsing from Scratch (2021.naacl-main)
Copied to clipboard
| Challenge: | Fig. 1 shows a document level discourse parser that performs top-down end-to-end parsing without requiring segmentation . |
| Approach: | They propose a top-down end-to-end formulation of document level discourse parsing in the Rhetorical Structure Theory framework. |
| Outcome: | The proposed model outperforms existing methods in end-to-end parsing and parse with gold segmentation without handcrafted features. |
RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators (2022.naacl-main)
Copied to clipboard
| Challenge: | Using a framework based on Rhetorical Structure Theory, we aim to improve the cohesion and coherence of long-form text generated by language models. |
| Approach: | They propose a framework that utilises Rhetorical Structure Theory to control the discourse structure, semantics and topics of generated text. |
| Outcome: | The proposed framework performs competitively against existing models while offering significantly more controls over generated text than alternative methods. |
Can we obtain significant success in RST discourse parsing by using Large Language Models? (2024.eacl-long)
Copied to clipboard
| Challenge: | Experimental results show that LLMs with tens of billion parameters can perform discourse parsing tasks. |
| Approach: | They employ Llama 2 and fine-tune it with QLoRA to achieve similar results . they show that LLMs with tens of billion parameters can perform a wide range of NLP tasks . |
| Outcome: | The proposed model performs better than existing models on three benchmark datasets. |
Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated Text Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to detect large language models (LLMs) use binary or ternary classifications, which can only distinguish pure human/LLM text or collaborative text at best. |
| Approach: | They propose a fine-grained method that characterizes distinct signatures of creator and editor by using Rhetorical Structure Theory to construct a logic graph for creator's foundation and extracting Elementary Discourse Unit (EDU)-level features for the editor's style. |
| Outcome: | The proposed method outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation. |
RST Discourse Parsing with Second-Stage EDU-Level Pre-training (2022.acl-long)
Copied to clipboard
| Challenge: | Existing pre-trained language models (PLMs) are based on sentence-level pre-training, which is different from the basic processing unit, i.e. element discourse unit (EDU). |
| Approach: | They propose a second-stage EDU-level pre-training approach to learn effective EDU representations continually based on well pre-trained language models. |
| Outcome: | The proposed method improves F1 score by 2.1 points on a benckmark dataset. |
Enhancing the AI2 Diagrams Dataset Using Rhetorical Structure Theory (L18-1)
Copied to clipboard
| Challenge: | Existing annotation schemas for diagrams are based on Rhetorical Structure Theory (RST) paper documents proposed schema, reports on inter-annotator agreement for this task, and discusses use of AI2D-RST for research on multimodality and artificial intelligence. |
| Approach: | They propose to replace the annotation of semantic relations between diagram elements by building on Rhetorical Structure Theory (RST) the paper documents the proposed annotation schema, describes challenges in applying RST to diagrams, and reports on inter-annotator agreement for this task. |
| Outcome: | The proposed schema is based on Rhetorical Structure Theory, which has been used to describe the multimodal structure of diagrams and documents. |
Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | Contemporary leading-edge systems for abstractive (long) text summarization employ Transformer encoderdecoder architectures that only consider the nuclearity annotation . |
| Approach: | They propose to incorporate Rhetorical Structure Theory into a novel summarization model that incorporates both the types and uncertainty of rhetorical relations. |
| Outcome: | The proposed model outperforms state-of-the-art models on automatic metrics and human evaluation. |
TreeAnnotator: Versatile Visual Annotation of Hierarchical Text Relations (L18-1)
Copied to clipboard
| Challenge: | TREEANNOTATOR is a browser-based tool for annotating tree-like structures . it provides a wider range of formats and provides graphical annotations . |
| Approach: | They evaluate TREEANNOTATOR, a browser-based tool for annotating tree-like structures, in particular structures that jointly map dependency relations and inclusion hierarchies, as used by Rhetorical Structure Theory. |
| Outcome: | The GUI interface is user-friendly and provides two visualization modes. |
Using Discourse Information for Education with a Spanish-Chinese Parallel Corpus (L18-1)
Copied to clipboard
| Challenge: | Discourse information is crucial for many NLP tasks due to the great distance that spans between the two languages. |
| Approach: | They propose to use a Spanish-Chinese parallel corpus with annotated discourse information to serve for bilingual language education. |
| Outcome: | The proposed corpus is composed of 100 Spanish-Chinese parallel texts, and all the discourse markers (DM) have been annotated to form the education source. |
A Unified Linear-Time Framework for Sentence-Level Discourse Parsing (P19-1)
Copied to clipboard
| Challenge: | a new neural framework for sentence-level discourse analysis is proposed . a discourse segmenter and a parser are based on pointer networks and operate in linear time . |
| Approach: | They propose a neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory . they use a discourse segmenter and a parser to construct a discursive tree in a top-down fashion . |
| Outcome: | The proposed framework surpasses previous approaches on both tasks and human agreement on both. |
Developing a Rhetorical Structure Theory Treebank for Czech (2024.lrec-main)
Copied to clipboard
| Challenge: | a paper on the Czech RST Discourse Treebank is the first version of a textual annotation system based on the Rhetorical Structure Theory . document is annotated using the RST, a global coherence model proposed by Mann and Thompson . |
| Approach: | They introduce the first version of the Czech RST Discourse Treebank . paper presents an annotation process and provides corpus statistics and evaluation . |
| Outcome: | The paper presents the first version of the Czech RST Discourse Treebank . the treebank includes two gold annotations representing divergent interpretations . |
DISRPT: A Multilingual, Multi-domain, Cross-framework Benchmark for Discourse Processing (2024.lrec-main)
Copied to clipboard
Chloé Braud, Amir Zeldes, Laura Rivière, Yang Janet Liu, Philippe Muller, Damien Sileo, Tatsuya Aoyama
| Challenge: | DISRPT is a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing. |
| Approach: | They present a multilingual, multi-domain, and cross-framework benchmark dataset for discourse processing that includes 13 languages and 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks. |
| Outcome: | The DISRPT dataset includes data from 24 corpora covering about 4 millions tokens and around 250,000 discourse relation instances from 4 discourse frameworks. |
Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing cross-document event coreference resolution models lack the ability to capture long-distance dependencies. |
| Approach: | They propose to construct document-level Rhetorical Structure Theory trees and cross-document Lexical Chains to model structural and semantic information of documents. |
| Outcome: | The proposed model outperforms baseline models on English and Chinese datasets by large margins. |
Bilingual Rhetorical Structure Parsing with Large Parallel Annotations (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing large RST corpora are inconsistent in annotation guidelines, genre representation, source selection, and relation definitions. |
| Approach: | They propose a parallel Russian annotation for a large and diverse English GUM RST corpus. |
| Outcome: | The proposed RST parser achieves state-of-the-art results on English and Russian corpus . it demonstrates effectiveness in monolingual and bilingual settings, transferring even with limited second-language annotation. |
Video Discourse Parsing and Its Application to Multimodal Summarization: A Dataset and Baseline Approaches (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Fig. 1 shows the video's story structure and event relationships in discourse parsing. |
| Approach: | They propose to construct an RST tree for a video to represent its storyline and illustrate the event relationships between events. |
| Outcome: | The proposed model outperforms two existing approaches to video RST parsing: the ‘parsing after captioning’ framework and parser using visual features. |
Split or Merge: Which is Better for Unsupervised RST Parsing? (D19-1)
Copied to clipboard
| Challenge: | Rhetorical Structure Theory (RST) parsers have been based on supervised learning approaches that require an annotated corpus of sufficient size and quality. |
| Approach: | They propose two unsupervised methods that build an optimal RST tree based on a dissimilarity score function for splitting a text span into smaller ones and a similarity score for merging two adjacent spans into a large one. |
| Outcome: | The proposed method achieves the best score on English and German RST treebanks, around 0.8 F1 score, close to the previous supervised parsers. |
Multilingual Neural RST Discourse Parsing (2020.coling-main)
Copied to clipboard
| Challenge: | Existing studies on text discourse parsing for English are limited due to the lack of annotated data. |
| Approach: | They propose to use multilingual vector representations and segment-level translation to establish a neural, cross-lingual discourse parser. |
| Outcome: | The proposed model achieves state-of-the-art on cross-lingual, document-level discourse parsing on all sub-tasks. |
A Pilot Study on Dialogue-Level Dependency Parsing for Chinese (2023.findings-acl)
Copied to clipboard
| Challenge: | Dialogue-level dependency parsing has received insufficient attention, especially for Chinese. |
| Approach: | They propose a signal-based method to transform seen syntactic dependencies into unseen ones between elementary discourse units (EDUs) they apply single-view and multi-view data selection to access reliable pseudo-labeled instances. |
| Outcome: | The proposed method transforms seen syntactic dependencies into unseen ones between elementary discourse units (EDUs) the proposed method also provides reliable pseudo-labeled instances. |
Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing long document question answering systems process texts as flat sequences or use heuristic chunking, which overlooks the discourse structures that guide human comprehension. |
| Approach: | They propose a discourse-aware hierarchical framework that leverages rhetorical structure theory for long document question answering. |
| Outcome: | The proposed framework exhibits strong robustness across diverse document types and linguistic settings. |
Discursive Circuits: How Do Language Models Understand Discourse Relations? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Discourse structure is essential for ensuring language models behave safely and ethically. |
| Approach: | They propose a task where a model completes a discourse given a specified relation . they propose CUDR task that enables activation patching to make circuit discovery feasible . |
| Outcome: | The proposed model recovers discourse understanding in the English PDTB-based CuDR task. |