论文标题
通过弹性重量巩固进行情感分析的顺序域适应
Sequential Domain Adaptation through Elastic Weight Consolidation for Sentiment Analysis
论文作者
论文摘要
弹性重量合并（EWC）是一种技术，用于克服在神经网络上训练的连续任务之间的灾难性遗忘。我们使用这种域之间的信息共享的信息共享。诸如情感分析（SA）之类的任务的培训数据可能不会在多个领域中得到公平代表。域的适应性（DA）旨在构建利用来自源域的信息来促进在看不见的目标域上的性能。我们提出了一个独立于模型的框架 - 顺序域适应（SDA）。 SDA利用EWC进行对连续的源域进行培训，以朝着通用域解决方案转向，从而解决了域的适应性问题。我们测试SDA关于卷积，经常性和基于注意力的架构的测试。我们的实验表明，所提出的框架可以使CNNS之类的简单体系结构在SA的域适应性中胜过更为复杂的最新模型。此外，我们观察到，源域的较难的第一抗辅助顺序有效性会导致最大的性能。
Elastic Weight Consolidation (EWC) is a technique used in overcoming catastrophic forgetting between successive tasks trained on a neural network. We use this phenomenon of information sharing between tasks for domain adaptation. Training data for tasks such as sentiment analysis (SA) may not be fairly represented across multiple domains. Domain Adaptation (DA) aims to build algorithms that leverage information from source domains to facilitate performance on an unseen target domain. We propose a model-independent framework - Sequential Domain Adaptation (SDA). SDA draws on EWC for training on successive source domains to move towards a general domain solution, thereby solving the problem of domain adaptation. We test SDA on convolutional, recurrent, and attention-based architectures. Our experiments show that the proposed framework enables simple architectures such as CNNs to outperform complex state-of-the-art models in domain adaptation of SA. In addition, we observe that the effectiveness of a harder first Anti-Curriculum ordering of source domains leads to maximum performance.
