A semantically enhanced dual encoder for aspect sentiment triplet extraction

TL;DR

This paper introduces a semantically enhanced dual encoder framework combining BERT, Bi-LSTM, and GCN to improve aspect sentiment triplet extraction by capturing multi-perspective semantic information, achieving state-of-the-art results.

Contribution

The novel framework integrates surface-level and deep semantic encoders with an interaction strategy, effectively capturing multi-perspective language features for better ASTE performance.

Findings

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

Effectively models syntactic and lexical information.

Enhances understanding of aspect-opinion relationships.

Abstract

Aspect sentiment triplet extraction (ASTE) is a crucial subtask of aspect-based sentiment analysis (ABSA) that aims to comprehensively identify sentiment triplets. Previous research has focused on enhancing ASTE through innovative table-filling strategies. However, these approaches often overlook the multi-perspective nature of language expressions, resulting in a loss of valuable interaction information between aspects and opinions. To address this limitation, we propose a framework that leverages both a basic encoder, primarily based on BERT, and a particular encoder comprising a Bi-LSTM network and graph convolutional network (GCN ). The basic encoder captures the surface-level semantics of linguistic expressions, while the particular encoder extracts deeper semantics, including syntactic and lexical information. By modeling the dependency tree of comments and considering the part-of-speech and positional information of words, we aim to capture semantics that are more relevant to the underlying intentions of the sentences. An interaction strategy combines the semantics learned by the two encoders, enabling the fusion of multiple perspectives and facilitating a more comprehensive understanding of aspect--opinion relationships. Experiments conducted on benchmark datasets demonstrate the state-of-the-art performance of our proposed framework.