| 引用本文: | 赵传君,孙绪壮,康璐,李旸,王素格,李德玉.基于高质量样本选择的跨领域方面级情感分析.软件学报,2026,37(4):1449-1471 |
| |
|
| |
|
|
| 本文已被：浏览 1892次 下载 1378次 |
码上扫一扫！ |
|
|
| 基于高质量样本选择的跨领域方面级情感分析 |
|
赵传君1,2, 孙绪壮1, 康璐1, 李旸3, 王素格4,5, 李德玉4,5
|
|
1.山西财经大学 信息学院, 山西 太原 030006;2.数据要素创新与经济决策分析山西省重点实验室(山西财经大学), 山西 太原 030006;3.山西财经大学 金融学院, 山西 太原 030006;4.山西大学 计算机与信息技术学院, 山西 太原 030006;5.计算智能与中文信息处理教育部重点实验室(山西大学), 山西 太原 030006
|
|
| 摘要: |
| 跨领域方面级情感分析利用源领域的已标注样本来帮助训练目标领域上的方面级情感分析任务, 但并非所有源领域样本均适合进行迁移训练, 部分样本会对迁移模型训练产生负迁移效应, 需要进行样本筛选工作. 现有的跨领域实例迁移方法所考虑的迁移依据比较片面, 忽略了样本间的协同作用, 影响跨领域泛化性能. 为了解决方面级情感分析任务中的特定领域训练样本匮乏与跨领域迁移中的样本筛选问题, 以多领域情感分析为开放环境, 结合高可信机器学习理论及建模中的领域适应方法, 提出一种基于高质量样本选择的跨领域方面级情感分析方法. 首先, 该方法分别设计了域间及域内高质量样本选择指标, 依次对源领域数据进行领域层面和样本层面的筛选, 兼顾了两种样本选择粒度的优势. 其次, 全面地设计了源领域与目标领域间相似性的衡量指标, 并通过图神经网络进行高效计算. 最后, 将多源领域迁移的场景纳入跨领域ABSA (aspect-based sentiment analysis)的讨论范围中, 设计了域间联合适应性分数, 通过平衡领域特征的重合性与差异性来选择领域间协同性高的多源领域组合. 在涵盖6个领域的基准数据集上设计了跨领域迁移任务, 并在方面级情感分析的3种子任务上进行了实验来验证所提方法的有效性. |
| 关键词: 跨领域方面级情感分析 高质量样本选择 领域适应 迁移学习 |
| DOI：10.13328/j.cnki.jos.007521 |
| 分类号:TP18 |
| 基金项目:国家自然科学基金(62376143, 62473241, 61906110); 山西省高等学校青年学术带头人项目(2024Q018); 山西省基础研究计划(202303021211139) |
|
| Cross-domain Aspect-based Sentiment Analysis Based on High-quality Sample Selection |
|
ZHAO Chuan-Jun1,2, SUN Xu-Zhuang1, KANG Lu1, LI Yang3, WANG Su-Ge4,5, LI De-Yu4,5
|
|
1.School of Information, Shanxi University of Finance and Economics, Taiyuan 030006, China;2.Shanxi Key Laboratory of Data Element Innovation and Economic Decision Analysis (Shanxi University of Finance and Economics), Taiyuan 030006, China;3.School of Finance, Shanxi University of Finance and Economics, Taiyuan 030006, China;4.School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China;5.Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education (Shanxi University), Taiyuan 030006, China
|
| Abstract: |
| Cross-domain aspect-based sentiment analysis (ABSA) uses annotated samples from the source domain to help train ABSA tasks on the target domain. However, not all samples from the source domain are suitable for transfer training, and some samples may have negative transfer effects on the training of the transfer model, which requires sample screening. Existing cross-domain instance transfer methods consider a one-sided transfer basis, ignoring the synergistic effect between samples and affecting cross-domain generalisation performance. In order to solve the problems of insufficient domain-specific training samples and sample screening in cross-domain transfer for ABSA tasks, this study proposes a cross-domain ABSA method based on high-quality sample selection by combining high-reliability machine learning theories and domain adaptation methods in modelling with the open environment of multi-domain sentiment analysis. First, inter-domain and intra-domain high-quality sample selection metrics are designed to filter the source domain data at the domain level and the sample level in turn, which takes into account the advantages of the two sample selection granularities. Second, similarity metrics between source and target domains are comprehensively designed and efficiently calculated through a graph neural network. Finally, the scenarios of multi-source domain transfer are included in the discussion of cross-domain ABSA, and inter-domain joint adaptability scores are designed to select the multi-source domain combinations with high inter-domain synergies by balancing the overlap and difference of domain features. A cross-domain transfer task is designed on a benchmark dataset covering six domains, and experiments are conducted on three sub-tasks of ABSA to validate the effectiveness of the proposed method. |
| Key words: cross-domain aspect-based sentiment analysis high-quality sample selection domain adaptation transfer learning |
|
|
|
|
