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 1909.04176cs.CLcs.LG
收藏

学习学习和预测:多标签分类的元学习方法

Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification

University of California, Santa Barbara(加州大学圣巴巴拉分校)

Jiawei Wu, Wenhan Xiong, William Yang Wang

摘要:

自然语言处理中的许多任务可以看作是多标签分类问题。然而,大多数现有模型都是用标准交叉熵损失函数训练的,并且使用固定的预测策略(例如,阈值为0.5),这完全忽略了不同标签之间的复杂性和依赖性。在本文中,我们提出了一种元学习方法来捕获这些复杂的标签依赖关系。更具体地说,我们的方法利用元学习器来联合学习不同标签的训练策略和预测策略。然后使用训练策略训练具有交叉熵损失函数的分类器,并且进一步实施预测策略以进行预测。在细粒度实体分类和文本分类上的实验结果表明,该方法可以获得更准确的多标签分类结果。

英文摘要:

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification 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。

↑