natural-language-processing

Discourse Parsing

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in discourse-parsing

Trend

Dataset

Best Model

Actions

RST-DT

Instructional-DT (Instr-DT)

STAC

Libraries

i

Use these libraries to find discourse-parsing models and implementations

Datasets

Molweni

RST-DT

GUM

AMALGUM

Instructional-DT (Instr-DT)

DISRPT2021

Subtasks

Discourse Segmentation Connective Detection

Most implemented papers

Fast Rhetorical Structure Theory Discourse Parsing

Michael Heilman, Kenji Sagae•Sat May 09 2015

An RST segmentation and parsing system that adapts models and feature sets from various previous work, as described below, that can process short documents such as news articles or essays in less than a second.

37

Content

Molweni

SPOT

PCC

0

Paper Graph

Representation Learning for Text-level Discourse Parsing

Jacob Eisenstein, Yangfeng Ji•Sat May 31 2014

A representation learning approach, in which surface features are transformed into a latent space that facilitates RST discourse parsing, which obtains substantial improvements over the previous state-of-the-art in predicting relations and nuclearity on the RST Treebank.

250 0

Paper Graph

A Unified Linear-Time Framework for Sentence-Level Discourse Parsing

Shafiq R. Joty, Xiang Lin, M Saiful Bari, Prathyusha Jwalapuram•Mon May 13 2019

An efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory that comprises a discourse segmenter to identify the elementary discourse units (EDU) in a text, and a discourse parser that constructs a discourse tree in a top-down fashion.

60 0

Paper Graph

ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences

Yanjun Gao, Ting-Hao 'Kenneth' Huang, R. Passonneau•Mon Jun 21 2021

This work proposes a new task to decompose each complex sentence into simple sentences derived from the tensed clauses in the source, and proposes a novel problem formulation as a graph edit task that learns to Accept, Break, Copy or Drop elements of a graph that combines word adjacency and grammatical dependencies.

15 0

Paper Graph

Multi-view and multi-task training of RST discourse parsers

Anders Søgaard, Barbara Plank, Chloé Braud•Wed Nov 30 2016

It is shown that a simple LSTM sequential discourse parser takes advantage of this multi-view and multi-task framework with 12-15% error reductions over the authors' baseline and results that rival more complex state-of-the-art parsers.

55 0

Paper Graph

The CLaC Discourse Parser at CoNLL-2015

Majid Laali, Leila Kosseim, Andre Cianflone•Tue Jun 30 2015

This paper describes the submission of the UIMA framework to the CoNLL-2015 shared task on shallow discourse parsing, and how it was used to develop the parser and to add machine learning functionality to the U IMA framework.

9 0

Paper Graph

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank

Kai Zhao, Liang Huang•Sun Aug 27 2017

This paper proposes the first end-to-end discourse parser that jointly parses in both syntax and discourse levels, as well as the first syntacto-discourse treebank by integrating the Penn Treebank and the RST Treebank.

19 0

Paper Graph

Cross-lingual RST Discourse Parsing

Anders Søgaard, Maximin Coavoux, Chloé Braud•Tue Jan 10 2017

A new discourse parser which is simpler, yet competitive (significantly better on 2/3 metrics) to state of the art for English, and a harmonization of discourse treebanks across languages are presented, enabling the first experiments on cross-lingual discourse parsing to be presented.

84 0

Paper Graph

The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error

Malihe Alikhani, Katherine Atwell, Anthony B. Sicilia, Seong Jae Hwang•Sun Mar 20 2022

It is found that non-news datasets are slightly easier to transfer to than news datasets when the training and test sets are very different, and a statistic from the theoretical domain adaptation literature which can be directly tied to error-gap is proposed.

17 0

Paper Graph

Adding a benchmark result helps the community track progress.