Inducing Target-Specific Latent Structures for Aspect Sentiment Classification

Chenhua Chen, Zhiyang Teng, Yue Zhang
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
Aspect-level sentiment analysis aims to recognize the sentiment polarity of an aspect or a target in a comment. Recently, graph convolutional networks based on linguistic dependency trees have been studied for this task. However, the dependency parsing accuracy of commercial product comments or tweets might be unsatisfactory. To tackle this problem, we associate linguistic dependency trees with automatically induced aspectspecific graphs. We propose gating mechanisms to dynamically combine
more » ... mation from word dependency graphs and latent graphs which are learned by self-attention networks. Our model can complement supervised syntactic features with latent semantic dependencies. Experimental results on five benchmarks show the effectiveness of our proposed latent models, giving significantly better results than models without using latent graphs.
doi:10.18653/v1/2020.emnlp-main.451 fatcat:uihrv7spkrbgfjcgcnnpu3lbjq