Extraction of Salient Sentences from Labelled Documents

TL;DR

This paper introduces a hierarchical convolutional model for extracting salient sentences from labeled documents, utilizing visualization techniques for interpretability and proposing a scalable evaluation method to assess extraction quality.

Contribution

The paper presents a novel hierarchical convolutional architecture combined with visualization methods and a scalable evaluation technique for sentence extraction.

Findings

Effective identification of topic-relevant sentences using visualization

Scalable evaluation method reduces reliance on manual annotation

Model supports interpretability of document structure

Abstract

We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure. Using this model, we show how to use visualisation techniques from the computer vision literature to identify and extract topic-relevant sentences. We also introduce a new scalable evaluation technique for automatic sentence extraction systems that avoids the need for time consuming human annotation of validation data.