Topological Sort for Sentence Ordering

  title={Topological Sort for Sentence Ordering},
  author={Shrimai Prabhumoye and R. Salakhutdinov and A. Black},
Sentence ordering is the task of arranging the sentences of a given text in the correct order. Recent work using deep neural networks for this task has framed it as a sequence prediction problem. In this paper, we propose a new framing of this task as a constraint solving problem and introduce a new technique to solve it. Additionally, we propose a human evaluation for this task. The results on both automatic and human metrics across four different datasets show that this new technique is… Expand
A Simple yet Effective Method for Sentence Ordering
Sentence ordering is the task of arranging a given bag of sentences so as to maximise the coherence of the overall text. In this work, we propose a simple yet effective training method that improvesExpand
BERT4SO: Neural Sentence Ordering by Fine-tuning BERT
This work proposes a new method, named BERT4SO, by fine-tuning BERT for sentence ordering by using multiple special tokens and carefully designed segment (interval) embeddings to concatenate all sentences and compute their representations. Expand
Neural Sentence Ordering Based on Constraint Graphs
This work devise a new approach based on multi-granular orders between sentences, which form multiple constraint graphs, which are then encoded by Graph Isomorphism Networks and fused into sentence representations, determined using the order-enhanced sentence representations. Expand
STaCK: Sentence Ordering with Temporal Commonsense Knowledge
Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document. Correctly ordering the sentences requires an understanding of coherence with respect toExpand
Reformulating Sentence Ordering as Conditional Text Generation
Reorder-Bart (RE-BART), a sentence ordering framework which leverages a pre-trained transformer-based model to identify a coherent order for a given set of shuffled sentences, is presented. Expand
A New Sentence Ordering Method using BERT Pretrained Model
Building systems with capability of natural language understanding (NLU) has been one of the oldest areas of AI. An essential component of NLU is to detect logical succession of events contained in aExpand
Ordering sentences and paragraphs with pre-trained encoder-decoder transformers and pointer ensembles
Passage ordering aims to maximise discourse coherence in document generation or document modification tasks such as summarisation or storytelling. This paper extends the passage ordering task fromExpand
InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?
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. Expand
BERT-enhanced Relational Sentence Ordering Network
A novel BERT-enhanced Relational Sentence Ordering Network (referred to as BRSON) is introduced by leveraging BERT for capturing better dependency relationship among sentences to enhance the coherence modeling for the entire paragraph. Expand
NAREOR: The Narrative Reordering Problem
This work presents a dataset, NAREORC, with over 1000 human rewritings of stories within ROCStories in non-linear orders, and proposes novel initial task-specific training methods and evaluation metrics. Expand


Neural Sentence Ordering
This work collects a large corpus of academic texts, and derive a data driven approach to learn pairwise ordering of sentences, and validate the efficacy with extensive experiments. Expand
Deep Attentive Sentence Ordering Network
In this paper, we propose a novel deep attentive sentence ordering network (referred as ATTOrderNet) which integrates self-attention mechanism with LSTMs in the encoding of input sentences. ItExpand
Sentence Ordering and Coherence Modeling using Recurrent Neural Networks
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. Expand
End-to-End Neural Sentence Ordering Using Pointer Network
An end-to-end neural approach to address the sentence ordering problem, which uses the pointer network (Ptr-Net) to alleviate the error propagation problem and utilize the whole contextual information is proposed. Expand
Probabilistic Text Structuring: Experiments with Sentence Ordering
An approach to information ordering that is particularly suited for text-to-text generation and the appropriateness of such a model for multidocument summarization is assessed. Expand
Inferring Strategies for Sentence Ordering in Multidocument News Summarization
A strategy for ordering information that combines constraints from chronological order of events and topical relatedness is implemented and Evaluation of the augmented algorithm shows a significant improvement of the ordering over two baseline strategies. Expand
Deep Attentive Ranking Networks for Learning to Order Sentences
This work presents an attention-based ranking framework for learning to order sentences given a paragraph, built on a bidirectional sentence encoder and a self-attention based transformer network that outperforms various state-of-the-art methods on these tasks on a variety of evaluation metrics. Expand
A Model of Coherence Based on Distributed Sentence Representation
A neural network model for the coherence task based on distributed sentence representation is introduced, which outperforms existing baselines and generates the state-of-art performance in standard coherence evaluation tasks. Expand
Concept-to-text Generation via Discriminative Reranking
A data-driven method for concept-to-text generation, the task of automatically producing textual output from non-linguistic input, that outperforms a competitive discriminative system both using BLEU and in a judgment elicitation study. Expand
SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents
We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable toExpand