文本分类(Text Classification)任务是根据给定文档的内容或主题,自动分配预先定义的类别标签。

VIP内容

深度神经网络对分类任务的预测准确度有显著的贡献。然而,他们倾向于在现实世界中做出过度自信的预测,其中存在领域转移和分布外(OOD)的例子。由于计算机视觉提供了对不确定性质量的视觉验证,目前对不确定性估计的研究主要集中在计算机视觉上。然而,在自然语言过程领域却鲜有研究。与贝叶斯方法通过权重不确定性间接推断不确定性不同,当前基于证据不确定性的方法通过主观意见明确地建模类别概率的不确定性。他们进一步考虑了不同根源的数据的固有不确定性,即vacuity(即由于缺乏证据而产生的不确定性)和不协调(即由于相互冲突的证据而产生的不确定性)。本文首次将证据不确定性运用于文本分类任务中的OOD检测。我们提出了一种既采用辅助离群样本,又采用伪离流形样本的廉价框架来训练具有特定类别先验知识的模型,该模型对OOD样本具有较高的空度。大量的经验实验表明,我们基于证据不确定性的模型在OOD实例检测方面优于其他同类模型。我们的方法可以很容易地部署到传统的循环神经网络和微调预训练的transformers。

https://www.zhuanzhi.ai/paper/f1ead8805294e050cc18d08d3f221296

成为VIP会员查看完整内容
0
10

最新内容

Deep learning has proven effective for various application tasks, but its applicability is limited by the reliance on annotated examples. Self-supervised learning has emerged as a promising direction to alleviate the supervision bottleneck, but existing work focuses on leveraging co-occurrences in unlabeled data for task-agnostic representation learning, as exemplified by masked language model pretraining. In this chapter, we explore task-specific self-supervision, which leverages domain knowledge to automatically annotate noisy training examples for end applications, either by introducing labeling functions for annotating individual instances, or by imposing constraints over interdependent label decisions. We first present deep probabilistic logic(DPL), which offers a unifying framework for task-specific self-supervision by composing probabilistic logic with deep learning. DPL represents unknown labels as latent variables and incorporates diverse self-supervision using probabilistic logic to train a deep neural network end-to-end using variational EM. Next, we present self-supervised self-supervision(S4), which adds to DPL the capability to learn new self-supervision automatically. Starting from an initial seed self-supervision, S4 iteratively uses the deep neural network to propose new self supervision. These are either added directly (a form of structured self-training) or verified by a human expert (as in feature-based active learning). Experiments on real-world applications such as biomedical machine reading and various text classification tasks show that task-specific self-supervision can effectively leverage domain expertise and often match the accuracy of supervised methods with a tiny fraction of human effort.

0
0
下载
预览

最新论文

Deep learning has proven effective for various application tasks, but its applicability is limited by the reliance on annotated examples. Self-supervised learning has emerged as a promising direction to alleviate the supervision bottleneck, but existing work focuses on leveraging co-occurrences in unlabeled data for task-agnostic representation learning, as exemplified by masked language model pretraining. In this chapter, we explore task-specific self-supervision, which leverages domain knowledge to automatically annotate noisy training examples for end applications, either by introducing labeling functions for annotating individual instances, or by imposing constraints over interdependent label decisions. We first present deep probabilistic logic(DPL), which offers a unifying framework for task-specific self-supervision by composing probabilistic logic with deep learning. DPL represents unknown labels as latent variables and incorporates diverse self-supervision using probabilistic logic to train a deep neural network end-to-end using variational EM. Next, we present self-supervised self-supervision(S4), which adds to DPL the capability to learn new self-supervision automatically. Starting from an initial seed self-supervision, S4 iteratively uses the deep neural network to propose new self supervision. These are either added directly (a form of structured self-training) or verified by a human expert (as in feature-based active learning). Experiments on real-world applications such as biomedical machine reading and various text classification tasks show that task-specific self-supervision can effectively leverage domain expertise and often match the accuracy of supervised methods with a tiny fraction of human effort.

0
0
下载
预览
Top