Boundary-Driven Table-Filling with Cross-Granularity Contrastive Learning for Aspect Sentiment Triplet Extraction

TL;DR

This paper introduces a novel boundary-driven table-filling approach with cross-granularity contrastive learning for aspect sentiment triplet extraction, effectively capturing both sentence-level and word-level semantics to improve performance.

Contribution

It proposes a boundary-driven table-filling method combined with cross-granularity contrastive learning and multi-scale convolution to enhance global and local semantic understanding in ASTE.

Findings

Achieves state-of-the-art F1 scores on benchmark datasets.

Effectively captures sentence-level and word-level semantic relations.

Improves extraction accuracy for complex multi-word aspect and opinion terms.

Abstract

The Aspect Sentiment Triplet Extraction (ASTE) task aims to extract aspect terms, opinion terms, and their corresponding sentiment polarity from a given sentence. It remains one of the most prominent subtasks in fine-grained sentiment analysis. Most existing approaches frame triplet extraction as a 2D table-filling process in an end-to-end manner, focusing primarily on word-level interactions while often overlooking sentence-level representations. This limitation hampers the model's ability to capture global contextual information, particularly when dealing with multi-word aspect and opinion terms in complex sentences. To address these issues, we propose boundary-driven table-filling with cross-granularity contrastive learning (BTF-CCL) to enhance the semantic consistency between sentence-level representations and word-level representations. By constructing positive and negative sample pairs, the model is forced to learn the associations at both the sentence level and the word level. Additionally, a multi-scale, multi-granularity convolutional method is proposed to capture rich semantic information better. Our approach can capture sentence-level contextual information more effectively while maintaining sensitivity to local details. Experimental results show that the proposed method achieves state-of-the-art performance on public benchmarks according to the F1 score.