Replicate, Walk, and Stop on Syntax: An Effective Neural Network Model for Aspect-Level Sentiment Classification

Authors

  • Yaowei Zheng Beihang University
  • Richong Zhang Beihang University
  • Samuel Mensah Beihang University
  • Yongyi Mao University of Ottawa

DOI:

https://doi.org/10.1609/aaai.v34i05.6517

Abstract

Aspect-level sentiment classification (ALSC) aims at predicting the sentiment polarity of a specific aspect term occurring in a sentence. This task requires learning a representation by aggregating the relevant contextual features concerning the aspect term. Existing methods cannot sufficiently leverage the syntactic structure of the sentence, and hence are difficult to distinguish different sentiments for multiple aspects in a sentence. We perceive the limitations of the previous methods and propose a hypothesis about finding crucial contextual information with the help of syntactic structure. For this purpose, we present a neural network model named RepWalk which performs a replicated random walk on a syntax graph, to effectively focus on the informative contextual words. Empirical studies show that our model outperforms recent models on most of the benchmark datasets for the ALSC task. The results suggest that our method for incorporating syntactic structure enriches the representation for the classification.

Downloads

Published

2020-04-03

How to Cite

Zheng, Y., Zhang, R., Mensah, S., & Mao, Y. (2020). Replicate, Walk, and Stop on Syntax: An Effective Neural Network Model for Aspect-Level Sentiment Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 9685-9692. https://doi.org/10.1609/aaai.v34i05.6517

Issue

Section

AAAI Technical Track: Natural Language Processing