Knowledge-enriched Two-layered Attention Network for Sentiment Analysis

TL;DR

This paper introduces a novel two-layered attention network enhanced with external knowledge from WordNet for sentiment analysis, achieving state-of-the-art results on the SemEval 2017 dataset.

Contribution

It presents a new two-layered attention model that incorporates external knowledge via Knowledge Graph Embeddings to improve sentiment prediction accuracy.

Findings

Outperforms the top system of SemEval 2017 Task 5

Improves state-of-the-art by 1.7 and 3.7 points on sub-tracks 1 and 2

Demonstrates the effectiveness of knowledge-enriched attention mechanisms

Abstract

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.