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 2107.07114cs.AI
收藏

不确定性感知的可靠文本分类

Uncertainty-Aware Reliable Text Classification

The University of Texas at Dallas(德克萨斯大学达拉斯分校)

Yibo Hu, Latifur Khan

摘要:

深度神经网络为分类任务的预测准确性做出了重大贡献。然而,他们往往会在现实世界的环境中做出过于自信的预测,其中存在域转移和分布外(OOD)的例子。不确定性估计的研究大多集中在计算机视觉上,因为它提供了对不确定性质量的视觉验证。然而,在自然语言过程域中,很少有人提出。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对类概率的不确定性进行建模。他们进一步考虑了数据中固有的不确定性,这些不确定性有不同的根本原因,空虚(即,由于缺乏证据的不确定性)和不和谐(即,由于证据的不确定性)。在本文中,我们首先将证据不确定性应用于文本分类任务的OOD检测。我们提出了一个廉价的框架,该框架采用辅助离群值和伪非流形样本来用某一类先验知识来训练模型,该模型对于OOD样本具有高真空度。大量的实证实验表明,我们的模型基于证据的不确定性优于其他同行检测OOD的例子。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变压器。

英文摘要:

Deep neural networks have significantly contributed to the success in predictive accuracy for classification tasks. However, they tend to make over-confident predictions in real-world settings, where domain shifting and out-of-distribution (OOD) examples exist. Most research on uncertainty estimation focuses on computer vision because it provides visual validation on uncertainty quality. However, few have been presented in the natural language process domain. Unlike Bayesian methods that indirectly infer uncertainty through weight uncertainties, current evidential uncertainty-based methods explicitly model the uncertainty of class probabilities through subjective opinions. They further consider inherent uncertainty in data with different root causes, vacuity (i.e., uncertainty due to a lack of evidence) and dissonance (i.e., uncertainty due to conflicting evidence). In our paper, we firstly apply evidential uncertainty in OOD detection for text classification tasks. We propose an inexpensive framework that adopts both auxiliary outliers and pseudo off-manifold samples to train the model with prior knowledge of a certain class, which has high vacuity for OOD samples. Extensive empirical experiments demonstrate that our model based on evidential uncertainty outperforms other counterparts for detecting OOD examples. Our approach can be easily deployed to traditional recurrent neural networks and fine-tuned pre-trained transformers.

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。

↑