Neural Subgraph Explorer: Reducing Noisy Information via Target-Oriented Syntax Graph Pruning

TL;DR

The paper introduces Neural Subgraph Explorer, a novel method that prunes syntax graphs to reduce noise and enhance target-oriented sentiment classification, achieving state-of-the-art results.

Contribution

It is the first to perform target-oriented syntax graph pruning, combining node relevance evaluation and first-order connection addition for improved sentiment analysis.

Findings

Achieves new state-of-the-art performance on benchmark datasets.

Effectively reduces noisy information in syntax graphs.

Enhances the capture of distant correlations in sentiment classification.

Abstract

Recent years have witnessed the emerging success of leveraging syntax graphs for the target sentiment classification task. However, we discover that existing syntax-based models suffer from two issues: noisy information aggregation and loss of distant correlations. In this paper, we propose a novel model termed Neural Subgraph Explorer, which (1) reduces the noisy information via pruning target-irrelevant nodes on the syntax graph; (2) introduces beneficial first-order connections between the target and its related words into the obtained graph. Specifically, we design a multi-hop actions score estimator to evaluate the value of each word regarding the specific target. The discrete action sequence is sampled through Gumble-Softmax and then used for both of the syntax graph and the self-attention graph. To introduce the first-order connections between the target and its relevant words, the two pruned graphs are merged. Finally, graph convolution is conducted on the obtained unified graph to update the hidden states. And this process is stacked with multiple layers. To our knowledge, this is the first attempt of target-oriented syntax graph pruning in this task. Experimental results demonstrate the superiority of our model, which achieves new state-of-the-art performance.