Sentence Ordering using Recurrent Neural Networks

By Lajanugen Logeswaran, Honglak Lee, Dragomir R. Radev. 2016

23 citations recorded by the source corpus.

Modeling the structure of coherent texts is a task of great importance in NLP. The task of organizing a given set of sentences into a coherent order has been commonly used to build and evaluate models that understand such structure. In this work we propose an end-to-end neural approach based on the recently proposed set to sequence mapping framework to address the sentence ordering problem. Our model achieves state-of-the-art performance in the order discrimination task on two datasets widely used in the literature. We also consider a new interesting task of ordering abstracts from conference papers and research proposals and demonstrate strong performance against recent methods. Visualizing the sentence representations learned by the model shows that the model has captured high level logical structure in these paragraphs. The model also learns rich semantic sentence representations by learning to order texts, performing comparably to recent unsupervised representation learning methods in the sentence similarity and paraphrase detection tasks.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning (2017, background): “Our system also compares favorably to the similar discourse-inspired method of Logeswaran et al. (2016), achieving similar results on MSRP in a sixth of their training time.”
Mining Discourse Markers for Unsupervised Sentence Representation Learning (2019, background): “In the same vein, Logeswaran et al. (2016) propose to predict if two sentences are consecutive, even though such local coherence can be straightforwardly predicted with relatively shallow features (Barzilay and Lapata, 2008).”