Deep learning models have performed well on many NLP tasks. However, their
internal mechanisms are typically difficult for humans to understand. The
development of methods to explain models has become a key issue in the
reliability of deep learning models in many important applications. Various
saliency explanation methods, which give each feature of input a score
proportional to the contribution of output, have been proposed to determine the
part of the input which a model values most. Despite a considerable body of
work on the evaluation of saliency methods, whether the results of various
evaluation metrics agree with human cognition remains an open question. In this
study, we propose a new human-based method to evaluate saliency methods in NLP
by crowdsourcing. We recruited 800 crowd workers and empirically evaluated
seven saliency methods on two datasets with the proposed method. We analyzed
the performance of saliency methods, compared our results with existing
automated evaluation methods, and identified notable differences between NLP
and computer vision (CV) fields when using saliency methods. The instance-level
data of our crowdsourced experiments and the code to reproduce the explanations
are available at this https URL

通过众包方法，我们提出了一种新的基于人类的自然语言处理（NLP）显著性方法评估方法，对七种显著性方法在两个数据集上进行了实证评估，与现有的自动评估方法进行了对比，发现了 NLP 和计算机视觉（CV）领域在使用显著性方法时存在显著差异。

通过众包评估自然语言处理中的显著性解释

Evaluating Saliency Explanations in NLP by Crowdsourcing

Trained classification models can unintentionally lead to biased
representations and predictions, which can reinforce societal preconceptions
and stereotypes. Existing debiasing methods for classification models, such as
adversarial training, are often expensive to train and difficult to optimise.
In this paper, we propose a method for mitigating bias in classifier training
by incorporating contrastive learning, in which instances sharing the same
class label are encouraged to have similar representations, while instances
sharing a protected attribute are forced further apart. In such a way our
method learns representations which capture the task label in focused regions,
while ensuring the protected attribute has diverse spread, and thus has limited
impact on prediction and thereby results in fairer models. Extensive
experimental results across four tasks in NLP and computer vision show (a) that
our proposed method can achieve fairer representations and realises bias
reductions compared with competitive baselines; and (b) that it can do so
without sacrificing main task performance; (c) that it sets a new
state-of-the-art performance in one task despite reducing the bias. Finally,
our method is conceptually simple and agnostic to network architectures, and
incurs minimal additional compute cost.

本论文提出了一种采用对比学习的分类器去偏置化的方法，使得模型在保持主要任务性能的前提下，更加公平地代表输入的各种属性，并取得了在 NLP 和计算机视觉四个任务中的优异表现。