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 1909.08167cs.LGcs.CLstat.ML
收藏

跨领域情感分析的加权领域不变表示学习

Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis

Fudan University(复旦大学)

Minlong Peng, Qi Zhang, Xuanjing Huang

摘要:

跨领域情感分析是当前研究和工程领域的一个热点。领域不变表示学习(DIRL)范式是该领域最流行的框架之一,它旨在学习跨领域的分布不变特征表示。然而,在这项工作中,我们发现,应用DIRL可能会损害领域自适应时,标签分布$\rm{P}(\rm{Y})$跨域的变化。为了解决这个问题,我们提出了一个修改DIRL,获得一个新的加权域不变表示学习(WDIRL)框架。我们表明,它是很容易将现有的SOTA DIRL模型WDIRL。大量跨领域情感分析任务的实证研究验证了我们的陈述,并显示了我们提出的解决方案的有效性。

英文摘要:

Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a distribution-invariant feature representation across domains. However, in this work, we find out that applying DIRL may harm domain adaptation when the label distribution $\rm{P}(\rm{Y})$ changes across domains. To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework. We show that it is easy to transfer existing SOTA DIRL models to WDIRL. Empirical studies on extensive cross-domain sentiment analysis tasks verified our statements and showed the effectiveness of our proposed solution.

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。

↑