SOTAVerified

Discourse Parsing

Papers

Showing 150 of 189 papers

TitleStatusHype
DMRST: A Joint Framework for Document-Level Multilingual RST Discourse Segmentation and ParsingCode1
On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation ClassificationCode1
Can we obtain significant success in RST discourse parsing by using Large Language Models?Code1
discopy: A Neural System for Shallow Discourse ParsingCode1
A Structure Self-Aware Model for Discourse Parsing on Multi-Party DialoguesCode1
ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over EventualitiesCode1
RST Parsing from ScratchCode1
Improving Multi-Party Dialogue Discourse Parsing via Domain IntegrationCode1
Fast Rhetorical Structure Theory Discourse ParsingCode1
Top-Down RST Parsing Utilizing Granularity Levels in DocumentsCode1
A Top-Down Neural Architecture towards Text-Level Parsing of Discourse Rhetorical StructureCode1
A Simple and Strong Baseline for End-to-End Neural RST-style Discourse ParsingCode1
ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple SentencesCode1
Top-down Discourse Parsing via Sequence LabellingCode1
Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation RecognitionCode1
RST Discourse Parsing with Second-Stage EDU-Level Pre-trainingCode1
Neural RST-based Evaluation of Discourse CoherenceCode1
Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse StructureCode1
Multilingual Neural RST Discourse ParsingCode1
GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse ParsingCode1
The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser ErrorCode0
STEM: Unsupervised STructural EMbedding for Stance DetectionCode0
The CLaC Discourse Parser at CoNLL-2015Code0
Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and BenchmarkCode0
RST-Tace A tool for automatic comparison and evaluation of RST treesCode0
A Distance-Aware Multi-Task Framework for Conversational Discourse ParsingCode0
A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational SpeechCode0
QUDEVAL: The Evaluation of Questions Under Discussion Discourse ParsingCode0
Structured Dialogue Discourse ParsingCode0
Representation Learning for Text-level Discourse ParsingCode0
Speaker-Aware Discourse Parsing on Multi-Party DialoguesCode0
CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversationsCode0
Multi-tasking Dialogue Comprehension with Discourse ParsingCode0
Persian Rhetorical Structure TheoryCode0
Learning Clause Representation from Dependency-Anchor Graph for Connective PredictionCode0
Joint Syntacto-Discourse Parsing and the Syntacto-Discourse TreebankCode0
Predicting Discourse Trees from Transformer-based Neural SummarizersCode0
GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and DomainsCode0
Bilingual Rhetorical Structure Parsing with Large Parallel AnnotationsCode0
A Deep Sequential Model for Discourse Parsing on Multi-Party DialoguesCode0
Does syntax help discourse segmentation? Not so muchCode0
MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment SupervisionCode0
GENTLE: A Genre-Diverse Multilayer Challenge Set for English NLP and Linguistic EvaluationCode0
Multi-view and multi-task training of RST discourse parsersCode0
DisCoDisCo at the DISRPT2021 Shared Task: A System for Discourse Segmentation, Classification, and Connective DetectionCode0
CoNLL 2016 Shared Task on Multilingual Shallow Discourse ParsingCode0
Deep Enhanced Representation for Implicit Discourse Relation RecognitionCode0
A Unified Linear-Time Framework for Sentence-Level Discourse ParsingCode0
Cross-lingual RST Discourse ParsingCode0
Hierarchical Pointer Net ParsingCode0
Show:102550
← PrevPage 1 of 4Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Top-down Span-based ParserRST-Parseval (Span)87Unverified
2Two-stage ParserRST-Parseval (Span)86Unverified
3Bottom-up Linear-chain CRF-based ParserRST-Parseval (Span)85.7Unverified
4Two-stage Discourse Parser with a Sliding WindowRST-Parseval (Span)83.84Unverified
5Guz et al. (2020) (pretrained)Standard Parseval (Span)72.94Unverified
6Guz et al. (2020)Standard Parseval (Span)72.43Unverified
7Top-down Span-based Parser with Silver Agreement Subtrees (ensemble)RST-Parseval (Full)62.6Unverified
8Top-down Span-based Parser with Silver Agreement SubtreesRST-Parseval (Full)61.8Unverified
9Transition-based Parser with Implicit Syntax FeaturesRST-Parseval (Full)59.9Unverified
10Bottom-up Llama 2 (70B)Standard Parseval (Full)58.1Unverified
#ModelMetricClaimedVerifiedStatus
1Bottom-up (DeBERTa)Standard Parseval (Nuclearity)60Unverified
2Top-down (DeBERTa)Standard Parseval (Nuclearity)57.9Unverified
3Bottom-up (XLNet)Standard Parseval (Nuclearity)56.4Unverified
4Top-down (RoBERTa)Standard Parseval (Nuclearity)56.1Unverified
5Bottom-up (RoBERTa)Standard Parseval (Nuclearity)55.5Unverified
6Top-down (XLNet)Standard Parseval (Nuclearity)55.2Unverified
7Top-down (SpanBERT)Standard Parseval (Nuclearity)54.5Unverified
8Bottom-up (SpanBERT)Standard Parseval (Nuclearity)53.8Unverified
9Guz et al. (2020) (pretrained)Standard Parseval (Nuclearity)46.59Unverified
10Bottom-up (BERT)Standard Parseval (Nuclearity)46.3Unverified
#ModelMetricClaimedVerifiedStatus
1DPLink & Rel F164.9Unverified
2StructuredLink & Rel F159.9Unverified
3SSP-BERT + SCIJELink & Rel F159.4Unverified
4HG-MDPLink & Rel F158.5Unverified
5Struct-AwareLink & Rel F158.4Unverified
6HierarchicalLink & Rel F156.1Unverified
7Deep SequentialLink & Rel F154.8Unverified
#ModelMetricClaimedVerifiedStatus
1StructuredLink & Rel F159.6Unverified
2SSP-BERT + SCIJELink & Rel F157.4Unverified
3Struct-AwareLink & Rel F157.3Unverified
4HierarchicalLink & Rel F157.2Unverified
5DiscProRecoLink & Rel F157Unverified
6Deep SequentialLink & Rel F155.7Unverified
7HG-MDPLink & Rel F155.6Unverified