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/Top-down Discourse Parsing via Sequence Labelling

Top-down Discourse Parsing via Sequence Labelling

Fajri Koto, Jey Han Lau, Timothy Baldwin

2021-02-03EACL 2021 2Discourse Parsing
PaperPDFCode(official)

Abstract

We introduce a top-down approach to discourse parsing that is conceptually simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020). By framing the task as a sequence labelling problem where the goal is to iteratively segment a document into individual discourse units, we are able to eliminate the decoder and reduce the search space for splitting points. We explore both traditional recurrent models and modern pre-trained transformer models for the task, and additionally introduce a novel dynamic oracle for top-down parsing. Based on the Full metric, our proposed LSTM model sets a new state-of-the-art for RST parsing.

Results

TaskDatasetMetricValueModel
Discourse ParsingRST-DTStandard Parseval (Full)50.3LSTM Dynamic
Discourse ParsingRST-DTStandard Parseval (Nuclearity)62.3LSTM Dynamic
Discourse ParsingRST-DTStandard Parseval (Relation)51.5LSTM Dynamic
Discourse ParsingRST-DTStandard Parseval (Span)73.1LSTM Dynamic
Discourse ParsingRST-DTStandard Parseval (Full)49.4LSTM Static
Discourse ParsingRST-DTStandard Parseval (Nuclearity)61.7LSTM Static
Discourse ParsingRST-DTStandard Parseval (Relation)50.5LSTM Static
Discourse ParsingRST-DTStandard Parseval (Span)72.7LSTM Static
Discourse ParsingRST-DTStandard Parseval (Full)49.2Transformer (dynamic)
Discourse ParsingRST-DTStandard Parseval (Nuclearity)60.1Transformer (dynamic)
Discourse ParsingRST-DTStandard Parseval (Span)70.2Transformer (dynamic)
Discourse ParsingRST-DTStandard Parseval (Full)49Transformer (static)
Discourse ParsingRST-DTStandard Parseval (Nuclearity)59.9Transformer (static)
Discourse ParsingRST-DTStandard Parseval (Relation)50.6Transformer (static)
Discourse ParsingRST-DTStandard Parseval (Span)70.6Transformer (static)

Related Papers

CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations2025-06-10ESURF: Simple and Effective EDU Segmentation2025-01-13Acquired TASTE: Multimodal Stance Detection with Textual and Structural Embeddings2024-12-04GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains2024-11-01Bilingual Rhetorical Structure Parsing with Large Parallel Annotations2024-09-23Llamipa: An Incremental Discourse Parser2024-06-26Unsupervised Mutual Learning of Dialogue Discourse Parsing and Topic Segmentation2024-05-30Can we obtain significant success in RST discourse parsing by using Large Language Models?2024-03-08