A Deep Neural Network Sentence Level Classification Method with Context Information
This addresses the problem of limited context usage in sentence classification for NLP researchers, but it is incremental as it builds on existing LSTM and CNN techniques.
The paper tackles sentence classification by incorporating large context information from adjacent sentences, achieving consistent improvements over previous methods on two datasets.
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.