Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet Extraction

2024-11-29

arXiv.org

AI Summary

Existing AOPE/ASTE methods predominantly adopt a pipelined extraction paradigm, which suffers from error propagation and high computational complexity. This paper proposes the first transition-based unified model for jointly extracting aspect-term–opinion-term–sentiment polarity triplets. Our approach addresses these limitations through three key innovations: (1) a position-aware transition system that explicitly models spatial relationships between aspects and opinions; (2) contrastive enhancement learning to foster cross-task synergy and mitigate entity-level bias; and (3) linear-time decoding for efficient inference. The model is jointly trained on four standard benchmarks. It achieves state-of-the-art F1 scores on both AOPE and ASTE, significantly outperforming prior best methods.

Technology Category

• Natural Language Processing: Information Extraction
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Knowledge Representation and Reasoning: Preferences

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Aspect-Opinion Pair Extraction (AOPE) and Aspect Sentiment Triplet Extraction (ASTE) have drawn growing attention in NLP. However, most existing approaches extract aspects and opinions independently, optionally adding pairwise relations, often leading to error propagation and high time complexity. To address these challenges and being inspired by transition-based dependency parsing, we propose the first transition-based model for AOPE and ASTE that performs aspect and opinion extraction jointly, which also better captures position-aware aspect-opinion relations and mitigates entity-level bias. By integrating contrastive-augmented optimization, our model delivers more accurate action predictions and jointly optimizes separate subtasks in linear time. Extensive experiments on 4 commonly used ASTE/AOPE datasets show that, while performing worse when trained on a single dataset than some previous models, our model achieves the best performance on both ASTE and AOPE if trained on combined datasets, outperforming the strongest previous models in F1-measures (often by a large margin). We hypothesize that this is due to our model's ability to learn transition actions from multiple datasets and domains. Our code is available at https://anonymous.4open.science/r/trans_aste-8FCF.

Problem

• Joint aspect-opinion extraction
• Transition-based model
• Linear time optimization

Innovation

• Transition-based model for AOPE
• Joint aspect-opinion extraction
• Contrastive-augmented optimization