Cached Long Short-Term Memory Neural Networks for Document-Level Sentiment Classification
This work addresses a specific bottleneck in sentiment analysis for long documents, offering an incremental improvement over existing methods.
The paper tackled the challenge of modeling long texts in document-level sentiment classification by proposing a Cached Long Short-Term Memory (CLSTM) neural network with a cache mechanism to better retain sentiment information, achieving state-of-the-art performance on three public datasets.
Recently, neural networks have achieved great success on sentiment classification due to their ability to alleviate feature engineering. However, one of the remaining challenges is to model long texts in document-level sentiment classification under a recurrent architecture because of the deficiency of the memory unit. To address this problem, we present a Cached Long Short-Term Memory neural networks (CLSTM) to capture the overall semantic information in long texts. CLSTM introduces a cache mechanism, which divides memory into several groups with different forgetting rates and thus enables the network to keep sentiment information better within a recurrent unit. The proposed CLSTM outperforms the state-of-the-art models on three publicly available document-level sentiment analysis datasets.