A Deep Neural Network Sentence Level Classification Method with Context Information

TL;DR

This paper introduces Context-LSTM-CNN, a novel sentence classification method that leverages large contextual information and long-range dependencies within sentences, improving accuracy over previous approaches.

Contribution

The paper presents a new neural network architecture combining LSTM and CNN to utilize extensive context and sentence features for improved classification.

Findings

Consistent performance improvement over previous methods

Effective use of large context in sentence classification

Demonstrated on two different datasets

Abstract

In the sentence classification task, context formed from sentences adjacent to the sentence being classified can provide important information for classification. This context is, however, often ignored. Where methods do make use of context, only small amounts are considered, making it difficult to scale. We present a new method for sentence classification, Context-LSTM-CNN, that makes use of potentially large contexts. The method also utilizes long-range dependencies within the sentence being classified, using an LSTM, and short-span features, using a stacked CNN. Our experiments demonstrate that this approach consistently improves over previous methods on two different datasets.