ZZU-NLP在SIGHAN-2024 dimABSA任务中：基于由粗到细上下文学习的方面级情感分析
ZZU-NLP at SIGHAN-2024 dimABSA Task: Aspect-Based Sentiment Analysis with Coarse-to-Fine In-context Learning
AI总结：
针对DimABSA细粒度情感强度预测任务，本文提出基于Baichuan2-7B的由粗到细上下文学习方法，通过固定示例初预测和BERT相似度筛选优化上下文示例，有效提升预测准确性与一致性。
摘要：
DimABSA任务要求对餐厅评论进行细粒度情感强度预测，包括为每个方面词（Aspect Term）预测效价（Valence）和唤醒度（Arousal）维度的分数。在本研究中，我们针对SIGHAN 2024研讨会中的DimABSA任务，提出了一种基于Baichuan2-7B模型的由粗到细上下文学习（Coarse-to-Fine In-context Learning，CFICL）方法。我们的方法通过两阶段优化过程提升预测准确性。在第一阶段，我们使用固定的上下文示例和提示模板来增强模型的情感识别能力，并为测试数据提供初始预测。在第二阶段，我们使用BERT对Opinion字段进行编码，并基于相似度选择最相似的训练数据作为新的上下文示例。这些示例包含Opinion字段及其分数，以及相关观点词及其平均分数。通过过滤情感极性，我们确保示例与测试数据保持一致。实验结果表明，我们的方法通过有效利用训练数据和优化上下文示例，显著提高了预测准确性和一致性。
英文摘要：
The DimABSA task requires fine-grained sentiment intensity prediction for restaurant reviews, including scores for Valence and Arousal dimensions for each Aspect Term. In this study, we propose a Coarse-to-Fine In-context Learning(CFICL) method based on the Baichuan2-7B model for the DimABSA task in the SIGHAN 2024 workshop. Our method improves prediction accuracy through a two-stage optimization process. In the first stage, we use fixed in-context examples and prompt templates to enhance the model's sentiment recognition capability and provide initial predictions for the test data. In the second stage, we encode the Opinion field using BERT and select the most similar training data as new in-context examples based on similarity. These examples include the Opinion field and its scores, as well as related opinion words and their average scores. By filtering for sentiment polarity, we ensure that the examples are consistent with the test data. Our method significantly improves prediction accuracy and consistency by effectively utilizing training data and optimizing in-context examples, as validated by experimental results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
