Knowledge-enriched Two-layered Attention Network for Sentiment Analysis
This work addresses sentiment analysis for natural language processing applications, presenting an incremental improvement over existing methods.
The paper tackles sentiment analysis by proposing a knowledge-enriched two-layered attention network based on Bidirectional LSTM, which improves sentiment prediction using external knowledge from WordNet. Experimental results on SemEval 2017 Task 5 show it surpasses the top system, improving state-of-the-art by 1.7 and 3.7 points for two sub-tracks.
We propose a novel two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis. The novel two-layered attention network takes advantage of the external knowledge bases to improve the sentiment prediction. It uses the Knowledge Graph Embedding generated using the WordNet. We build our model by combining the two-layered attention network with the supervised model based on Support Vector Regression using a Multilayer Perceptron network for sentiment analysis. We evaluate our model on the benchmark dataset of SemEval 2017 Task 5. Experimental results show that the proposed model surpasses the top system of SemEval 2017 Task 5. The model performs significantly better by improving the state-of-the-art system at SemEval 2017 Task 5 by 1.7 and 3.7 points for sub-tracks 1 and 2 respectively.