TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/RST Parsing from Scratch

RST Parsing from Scratch

Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, XiaoLi Li

2021-05-23NAACL 2021 4SegmentationDiscourse ParsingEnd-to-End RST ParsingDiscourse Segmentation
PaperPDFCode(official)

Abstract

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.

Results

TaskDatasetMetricValueModel
Discourse ParsingRST-DTRST-Parseval (Nuclearity)76End-to-end Top-down (XLNet)
Discourse ParsingRST-DTRST-Parseval (Relation)61.8End-to-end Top-down (XLNet)
Discourse ParsingRST-DTRST-Parseval (Span)87.6End-to-end Top-down (XLNet)
Discourse ParsingRST-DTStandard Parseval (Full)50.2End-to-end Top-down (XLNet)
Discourse ParsingRST-DTStandard Parseval (Nuclearity)64.3End-to-end Top-down (XLNet)
Discourse ParsingRST-DTStandard Parseval (Relation)51.6End-to-end Top-down (XLNet)
Discourse ParsingRST-DTStandard Parseval (Span)74.3End-to-end Top-down (XLNet)
Discourse ParsingRST-DTStandard Parseval (Full)46.8End-to-end Top-down (Glove)
Discourse ParsingRST-DTStandard Parseval (Nuclearity)59.6End-to-end Top-down (Glove)
Discourse ParsingRST-DTStandard Parseval (Relation)47.7End-to-end Top-down (Glove)
Discourse ParsingRST-DTStandard Parseval (Span)71.1End-to-end Top-down (Glove)
Discourse ParsingRST-DTStandard Parseval (Full)46.6Nguyen et al. (2021)
Discourse ParsingRST-DTStandard Parseval (Nuclearity)59.1Nguyen et al. (2021)
Discourse ParsingRST-DTStandard Parseval (Relation)47.8Nguyen et al. (2021)
Discourse ParsingRST-DTStandard Parseval (Span)68.4Nguyen et al. (2021)

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17