先生成再全局修正，提升情感四元组预测准确率
Generate Then Correct: Single Shot Global Correction for Aspect Sentiment Quad Prediction
- 先生成四元组，再用全局修正模型一次性纠错
- 在Rest15和Rest16数据集上超越强基线模型
- 适合需要高精度情感分析的应用场景
基于方面的情感分析（ABSA）从用户生成文本中提取细粒度情感信号，支持产品分析、体验监控和舆情追踪，是细粒度意见挖掘的核心任务。关键挑战在于方面情感四元组预测（ASQP），需同时识别方面项、方面类别、观点项和情感极性。现有方法通常将无序四元组线性化为固定顺序模板，并采用自回归方式从左到右解码，导致训练与推理不一致（暴露偏差），早期错误会传播至后续元素。由于线性化顺序决定了前缀中元素的出现位置，这种传播具有顺序敏感性，难以在单次遍历中修复。为此，我们提出生成-纠正（G2C）方法：生成器先草拟四元组，校正器则基于大模型合成的含典型错误样本进行单次、序列级全局校正。在Rest15和Rest16数据集上，G2C显著优于多个强基线模型。
原文摘要 · Abstract (English)
Aspect-based sentiment analysis (ABSA) extracts aspect-level sentiment signals from user-generated text, supports product analytics, experience monitoring, and public-opinion tracking, and is central to fine-grained opinion mining. A key challenge in ABSA is aspect sentiment quad prediction (ASQP), which requires identifying four elements: the aspect term, the aspect category, the opinion term, and the sentiment polarity. However, existing studies usually linearize the unordered quad set into a fixed-order template and decode it left-to-right. With teacher forcing training, the resulting training-inference mismatch (exposure bias) lets early prefix errors propagate to later elements. The linearization order determines which elements appear earlier in the prefix, so this propagation becomes order-sensitive and is hard to repair in a single pass. To address this, we propose a method, Generate-then-Correct (G2C): a generator drafts quads and a corrector performs a single-shot, sequence-level global correction trained on LLM-synthesized drafts with common error patterns. On the Rest15 and Rest16 datasets, G2C outperforms strong baseline models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。