Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network

TL;DR

This paper introduces a hierarchical convolutional neural network model for document representation that captures semantic nuances and order, enabling effective visualization and automatic summarization without feature engineering.

Contribution

The paper presents an extended dynamic CNN that hierarchically learns semantic features at sentence and document levels, with a novel visualization technique for interpretability and summarization.

Findings

Achieves strong results on document modeling tasks

Provides a new visualization method for CNNs in NLP

Enables automatic text summarization

Abstract

Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval. We introduce a model that is able to represent the meaning of documents by embedding them in a low dimensional vector space, while preserving distinctions of word and sentence order crucial for capturing nuanced semantics. Our model is based on an extended Dynamic Convolution Neural Network, which learns convolution filters at both the sentence and document level, hierarchically learning to capture and compose low level lexical features into high level semantic concepts. We demonstrate the effectiveness of this model on a range of document modelling tasks, achieving strong results with no feature engineering and with a more compact model. Inspired by recent advances in visualising deep convolution networks for computer vision, we present a novel visualisation technique for our document networks which not only provides insight into their learning process, but also can be interpreted to produce a compelling automatic summarisation system for texts.