Lexicon Integrated CNN Models with Attention for Sentiment Analysis
This work addresses sentiment analysis for NLP applications, offering an incremental improvement by combining existing lexicon and attention techniques.
The paper tackles sentiment analysis by integrating lexicon embeddings and an attention mechanism into CNNs, achieving comparative or better results on SemEval'16 and Stanford Sentiment Treebank datasets, with analysis showing lexicon embeddings enable high performance with smaller word embeddings and attention reduces noise.
With the advent of word embeddings, lexicons are no longer fully utilized for sentiment analysis although they still provide important features in the traditional setting. This paper introduces a novel approach to sentiment analysis that integrates lexicon embeddings and an attention mechanism into Convolutional Neural Networks. Our approach performs separate convolutions for word and lexicon embeddings and provides a global view of the document using attention. Our models are experimented on both the SemEval'16 Task 4 dataset and the Stanford Sentiment Treebank, and show comparative or better results against the existing state-of-the-art systems. Our analysis shows that lexicon embeddings allow to build high-performing models with much smaller word embeddings, and the attention mechanism effectively dims out noisy words for sentiment analysis.