Prompt Based Tri-Channel Graph Convolution Neural Network for Aspect Sentiment Triplet Extraction

TL;DR

This paper introduces PT-GCN, a novel graph-based neural network that models relational information as a graph for improved aspect sentiment triplet extraction, achieving state-of-the-art results.

Contribution

The paper proposes a prompt-based tri-channel graph convolution model that captures deep interactions in relation tables for ASTE, surpassing prior table-filling methods.

Findings

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

Effectively models relational information with a graph structure.

Demonstrates the benefit of deep interaction modeling in ASTE.

Abstract

Aspect Sentiment Triplet Extraction (ASTE) is an emerging task to extract a given sentence's triplets, which consist of aspects, opinions, and sentiments. Recent studies tend to address this task with a table-filling paradigm, wherein word relations are encoded in a two-dimensional table, and the process involves clarifying all the individual cells to extract triples. However, these studies ignore the deep interaction between neighbor cells, which we find quite helpful for accurate extraction. To this end, we propose a novel model for the ASTE task, called Prompt-based Tri-Channel Graph Convolution Neural Network (PT-GCN), which converts the relation table into a graph to explore more comprehensive relational information. Specifically, we treat the original table cells as nodes and utilize a prompt attention score computation module to determine the edges' weights. This enables us to construct a target-aware grid-like graph to enhance the overall extraction process. After that, a triple-channel convolution module is conducted to extract precise sentiment knowledge. Extensive experiments on the benchmark datasets show that our model achieves state-of-the-art performance. The code is available at https://github.com/KunPunCN/PT-GCN.