natural-language-processing-10

Discourse Segmentation

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-segmentation-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find discourse-segmentation-10 models and implementations

Datasets

GUM

AMALGUM

DISRPT2019

DISRPT2021

Subtasks

No subtasks available.

Most implemented papers

Two-pass Discourse Segmentation with Pairing and Global Features

Graeme Hirst, V. Feng•Tue Jul 29 2014

It is shown that both the pairing and global features are useful on their own, and their combination achieved an F1 of 92.6% of identifying insentence discourse boundaries, which is a 17.8% error-rate reduction over the state of the art performance.

18

Content

0

Paper Graph

Cross-lingual and cross-domain discourse segmentation of entire documents

Anders Søgaard, Ophélie Lacroix, Chloé Braud•Wed Apr 12 2017

This paper proposes statistical discourse segmenters for five languages and three domains that do not rely on gold pre-annotations, and considers the problem of learning discourse segmenter when no labeled data is available for a language.

36 0

Paper Graph

Does syntax help discourse segmentation? Not so much

Anders Søgaard, Ophélie Lacroix, Chloé Braud•Thu Aug 31 2017

The results show that dependency information is less useful than expected, but the model provided is a fully scalable, robust model that only relies on part-of-speech information, and it performs well across languages in the absence of any gold-standard annotation.

15 0

Paper Graph

Toward Fast and Accurate Neural Discourse Segmentation

Yizhong Wang, Sujian Li, Jingfeng Yang•Mon Aug 27 2018

This paper proposes an end-to-end neural segmenter based on BiLSTM-CRF framework that addresses the problem of data insufficiency by transferring a word representation model that is trained on a large corpus and proposes a restricted self-attention mechanism in order to capture useful information within a neighborhood.

100 0

Paper Graph

From News to Medical: Cross-domain Discourse Segmentation

K. Erk, Junyi Jessy Li, Elisa Ferracane, Titan Page•Mon Dec 31 2018

This work annotates the first high-quality small-scale medical corpus in English with discourse segments and analyzes how well news-trained segmenters perform on this domain.

4 0

Paper Graph

Text Segmentation by Cross Segment Attention

Michal Lukasik, Boris Dadachev, Gonçalo Simões, Kishore Papineni•Tue Mar 31 2020

This work proposes three transformer-based architectures and provides comprehensive comparisons with previously proposed approaches on three standard datasets, and establishes a new state-of-the-art, reducing in particular the error rates by a large margin in all cases.

106 0

Paper Graph

Joint Learning of Syntactic Features Helps Discourse Segmentation

D. Moldovan, Parag Dakle, Takshak Desai•Thu Apr 30 2020

An accurate framework for carrying out multi-lingual discourse segmentation with BERT is described, trained to identify segments by casting the problem as a token classification problem and jointly learning syntactic features like part-of-speech tags and dependency relations.

7 0

Paper Graph

Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading

S. Hoi, Caiming Xiong, Irwin King, Shafiq R. Joty, Chien-Sheng Wu, Yifan Gao, Jingjing Li, M. Lyu•Sun Oct 04 2020

This work proposes Discern, a discourse-aware entailment reasoning network to strengthen the connection and enhance the understanding for both document and dialog, and splits the document into clause-like elementary discourse units using a pre-trained discourse segmentation model.

53 0

Paper Graph

Open-Retrieval Conversational Machine Reading

Irwin King, Yifan Gao, Jingjing Li, M. Lyu•Tue Feb 16 2021

MUDERN is proposed, a Multi-passage Discourse-aware Entailment Reasoning Network which extracts conditions in the rule texts through discourse segmentation, conducts multi-passages entailment reasoning to answer user questions directly, or asks clarification follow-up questions to inquiry more information.

18 0

Paper Graph

Adding a benchmark result helps the community track progress.