natural-language-processing-8

Sentence Ordering

3260 papers • 126 benchmarks • 313 datasets

Sentence ordering task deals with finding the correct order of sentences given a randomly ordered paragraph.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in sentence-ordering-8

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find sentence-ordering-8 models and implementations

Datasets

OrdinalDataset

Subtasks

No subtasks available.

Most implemented papers

Sentence Ordering and Coherence Modeling using Recurrent Neural Networks

Honglak Lee, Dragomir R. Radev, Lajanugen Logeswaran•Mon Nov 07 2016

This work proposes an end- to-end unsupervised deep learning approach based on the set-to-sequence framework to address the structure of coherent texts and shows that useful text representations can be obtained by learning to order sentences.

119

Content

0

Paper Graph

InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?

Fang Wu, Xiang Bai•Thu Dec 31 2020

This paper proposes InsertGNN, a simple yet effective model that represents the problem as a graph and adopts the Graph Neural Network (GNN) to learn the connection between sentences and achieves an accuracy of 70%, rivaling the average human test scores.

0 0

Paper Graph

Topological Sort for Sentence Ordering

R. Salakhutdinov, A. Black, Shrimai Prabhumoye•Thu Apr 30 2020

The results on both automatic and human metrics across four different datasets show that this new technique to solve sentence ordering is better at capturing coherence in documents.

54 0

Paper Graph

Text Coherence Analysis Based on Deep Neural Network

Baiyun Cui, Yingming Li, Yaqing Zhang, Zhongfei Zhang•Fri Oct 20 2017

A novel deep coherence model (DCM) using a convolutional neural network architecture to capture the text coherence and can be easily trained in an end-to-end fashion.

37 0

Paper Graph

Partially Shuffling the Training Data to Improve Language Models

•Sun Mar 10 2019

This paper presents a method that partially shuffles the training data between epochs, which makes each batch random, while keeping most sentence ordering intact, and achieves new state of the art results on word-level language modeling on both the Penn Treebank and WikiText-2 datasets.

6 0

Paper Graph

Graph-based Neural Sentence Ordering

Jiebo Luo, Linfeng Song, Yongjing Yin, Jinsong Su, Jiali Zeng, Chulun Zhou•Wed Jul 31 2019

A novel and flexible graph-based neural sentence ordering model, which adopts graph recurrent network \cite{Zhang:acl18} to accurately learn semantic representations of the sentences, which outperforms the existing state-of-the-art systems on several benchmark datasets.

70 0

Paper Graph

On Losses for Modern Language Models

Stephane T Aroca-Ouellette, Frank Rudzicz•Sat Oct 03 2020

It is shown that NSP is detrimental to training due to its context splitting and shallow semantic signal, and it is demonstrated that using multiple tasks in a multi-task pre-training framework provides better results than using any single auxiliary task.

36 0

Paper Graph

Neural Sentence Ordering Based on Constraint Graphs

Shengchao Liu, Yutao Zhu, Zhicheng Dou, Kun Zhou, J. Nie•Tue Jan 26 2021

This work devise a new approach based on multi-granular orders between sentences, which form multiple constraint graphs, which are encoded by Graph Isomorphism Networks and fused into sentence representations, determined using the order-enhanced sentence representations.

23 0

Paper Graph

Is Everything in Order? A Simple Way to Order Sentences

Snigdha Chaturvedi, Faeze Brahman, Somnath Basu Roy Chowdhury•Tue Apr 13 2021

Reorder-Bart (Re-BART) is presented, that leverages a pre-trained Transformer-based model to identify a coherent order for a given set of shuffled sentences and achieves the state-of-the-art performance across 7 datasets in Perfect Match Ratio (PMR) and Kendall's tau.

28 0

Paper Graph

STaCK: Sentence Ordering with Temporal Commonsense Knowledge

Soujanya Poria, Navonil Majumder, Deepanway Ghosal, Rada Mihalcea•Sun Sep 05 2021

STaCK is introduced — a framework based on graph neural networks and temporal commonsense knowledge to model global information and predict the relative order of sentences and results are reported on five different datasets.

12 0

Paper Graph

Adding a benchmark result helps the community track progress.