arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.07804cs.CL
收藏

学习通过软标签和流形混淆对开放意图进行分类

Learning to Classify Open Intent via Soft Labeling and Manifold Mixup

Nanjing University(南京大学)

Zifeng Cheng, Zhiwei Jiang, Yafeng Yin, Cong Wang, Qing Gu

摘要:

开放意图分类是对话系统中一项实用而又具有挑战性的任务。它的目标是准确地分类已知意图的样本,同时检测开放(未知)意图的样本。现有的方法通常使用离群检测算法结合K类分类器来检测开放意图,其中K表示已知意图的类别数。与他们不同的是,本文考虑了另一种不使用离群值检测算法的方法。具体地,我们直接训练用于开放意图分类的(K+1)类分类器,其中第(K+1)类表示开放意图。为了解决仅使用K类训练样本训练(K+1)类分类器的挑战,我们提出了一种基于软标记和流形混合(SLMM)的深度模型。在我们的方法中,软标记被用来重塑已知意图样本的标签分布,旨在减少模型对已知意图的过度自信。为了更好地优化开放意图的决策边界,采用流形混合算法生成开放意图的伪样本。在四个基准数据集上的实验表明,我们的方法优于以前的方法,并达到了最先进的性能。本工作的所有代码和数据可以在https://github.com/zifengcheng/SLMM上获得。

英文摘要:

Open intent classification is a practical yet challenging task in dialogue systems. Its objective is to accurately classify samples of known intents while at the same time detecting those of open (unknown) intents. Existing methods usually use outlier detection algorithms combined with K-class classifier to detect open intents, where K represents the class number of known intents. Different from them, in this paper, we consider another way without using outlier detection algorithms. Specifically, we directly train a (K+1)-class classifier for open intent classification, where the (K+1)-th class represents open intents. To address the challenge that training a (K+1)-class classifier with training samples of only K classes, we propose a deep model based on Soft Labeling and Manifold Mixup (SLMM). In our method, soft labeling is used to reshape the label distribution of the known intent samples, aiming at reducing model's overconfident on known intents. Manifold mixup is used to generate pseudo samples for open intents, aiming at well optimizing the decision boundary of open intents. Experiments on four benchmark datasets demonstrate that our method outperforms previous methods and achieves state-of-the-art performance. All the code and data of this work can be obtained at https://github.com/zifengcheng/SLMM.

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。

↑