arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1908.09122cs.CL
收藏

跨领域情感分类的领域不变特征提取

Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification

Nankai University(南开大学);IBM Research - China(IBM中国研究院)

Mengting Hu, Yike Wu, Shiwan Zhao, Honglei Guo, Renhong Cheng, Zhong Su

摘要:

跨领域情感分类近年来受到了广泛的关注。现有的方法大多集中在学习领域不变的表示在源和目标领域,而很少有人注意到特定领域的信息。尽管领域特定信息的不可传递性,同时学习领域相关表示可以促进领域不变表示的学习。在本文中,我们专注于方面级别的跨领域的情感分类,并提出了提取领域不变的情感特征的帮助下,一个正交的领域相关的任务,即方面检测,这是建立在方面在不同的领域变化很大。我们在三个公开数据集上进行了大量的实验,实验结果证明了我们的方法的有效性。

英文摘要:

Cross-domain sentiment classification has drawn much attention in recent years. Most existing approaches focus on learning domain-invariant representations in both the source and target domains, while few of them pay attention to the domain-specific information. Despite the non-transferability of the domain-specific information, simultaneously learning domain-dependent representations can facilitate the learning of domain-invariant representations. In this paper, we focus on aspect-level cross-domain sentiment classification, and propose to distill the domain-invariant sentiment features with the help of an orthogonal domain-dependent task, i.e. aspect detection, which is built on the aspects varying widely in different domains. We conduct extensive experiments on three public datasets and the experimental results demonstrate the effectiveness of our method.

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。

↑