Sentence Ordering

20 papers with code • 0 benchmarks • 1 datasets

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

Most implemented papers

Topological Sort for Sentence Ordering

shrimai/Topological-Sort-for-Sentence-Ordering ACL 2020

Sentence ordering is the task of arranging the sentences of a given text in the correct order.

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

smiles724/toefl-sentence-insertion-dataset 28 Mar 2021

Sentence insertion is an interesting NLP problem but received insufficient attention.

Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction

chongzhangfdu/tpp 17 Oct 2023

However, BIO-tagging scheme relies on the correct order of model inputs, which is not guaranteed in real-world NER on scanned VrDs where text are recognized and arranged by OCR systems.

Text Coherence Analysis Based on Deep Neural Network

geekSiddharth/DeepCoherence 21 Oct 2017

In this paper, we propose a novel deep coherence model (DCM) using a convolutional neural network architecture to capture the text coherence.

Partially Shuffling the Training Data to Improve Language Models

ofirpress/PartialShuffle arXiv 2019

Although SGD requires shuffling the training data between epochs, currently none of the word-level language modeling systems do this.

Graph-based Neural Sentence Ordering

DeepLearnXMU/NSEG 16 Dec 2019

Sentence ordering is to restore the original paragraph from a set of sentences.

On Losses for Modern Language Models

StephAO/olfmlm EMNLP 2020

BERT set many state-of-the-art results over varied NLU benchmarks by pre-training over two tasks: masked language modelling (MLM) and next sentence prediction (NSP), the latter of which has been highly criticized.

Neural Sentence Ordering Based on Constraint Graphs

DaoD/ConstraintGraph4NSO 27 Jan 2021

Our experiments on five benchmark datasets show that our method outperforms all the existing baselines significantly, achieving a new state-of-the-art performance.

Is Everything in Order? A Simple Way to Order Sentences

fabrahman/rebart EMNLP 2021

We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets.