Table-Filling via Mean Teacher for Cross-domain Aspect Sentiment Triplet Extraction

TL;DR

This paper introduces TFMT, a novel table-filling method inspired by object detection, for cross-domain aspect sentiment triplet extraction, effectively reducing computational costs and addressing domain shift issues.

Contribution

The paper proposes TFMT, a new OD-inspired table-filling approach with region-level and domain-level consistency for cross-domain ASTE, outperforming existing methods.

Findings

Achieves state-of-the-art performance on cross-domain ASTE tasks.

Reduces computational costs compared to synthetic data generation methods.

Effectively mitigates domain shift with MMD-based domain adaptation.

Abstract

Cross-domain Aspect Sentiment Triplet Extraction (ASTE) aims to extract fine-grained sentiment elements from target domain sentences by leveraging the knowledge acquired from the source domain. Due to the absence of labeled data in the target domain, recent studies tend to rely on pre-trained language models to generate large amounts of synthetic data for training purposes. However, these approaches entail additional computational costs associated with the generation process. Different from them, we discover a striking resemblance between table-filling methods in ASTE and two-stage Object Detection (OD) in computer vision, which inspires us to revisit the cross-domain ASTE task and approach it from an OD standpoint. This allows the model to benefit from the OD extraction paradigm and region-level alignment. Building upon this premise, we propose a novel method named \textbf{T}able-\textbf{F}illing via \textbf{M}ean \textbf{T}eacher (TFMT). Specifically, the table-filling methods encode the sentence into a 2D table to detect word relations, while TFMT treats the table as a feature map and utilizes a region consistency to enhance the quality of those generated pseudo labels. Additionally, considering the existence of the domain gap, a cross-domain consistency based on Maximum Mean Discrepancy is designed to alleviate domain shift problems. Our method achieves state-of-the-art performance with minimal parameters and computational costs, making it a strong baseline for cross-domain ASTE.