论文标题
订单敏感的沙普利值，用于评估NLP模型的概念性声音
Order-sensitive Shapley Values for Evaluating Conceptual Soundness of NLP Models
论文作者
论文摘要
先前的作品表明，深度NLP模型并不总是在概念上是合理的：它们并不总是学习正确的语言概念。具体来说，它们可能对单词顺序不敏感。为了系统地评估其相对于单词顺序的概念性声音的模型，我们引入了一种新的解释方法，以实现顺序数据：对订单敏感的Shapley值（OSV）。我们进行了广泛的经验评估，以验证各种深度NLP模型学习单词顺序的方法和表现。使用合成数据，我们首先表明OSV比基于梯度的方法更忠实地解释模型行为。其次，应用于HANS数据集，我们发现基于BERT的NLI模型仅使用无单词顺序的单词出现。尽管简单的数据增强提高了汉斯的准确性，但OSV表明，增强模型并不能从根本上改善模型的顺序学习。第三，我们发现并非所有的情感分析模型都正确地学习否定：有些人无法捕获否定结构的正确语法。最后，我们表明，诸如BERT之类的验证语言模型可能依赖主题词的绝对立场来学习长期主题 - 动词的一致性。通过每个NLP任务，我们还演示了如何利用OSV来生成对抗性示例。
Previous works show that deep NLP models are not always conceptually sound: they do not always learn the correct linguistic concepts. Specifically, they can be insensitive to word order. In order to systematically evaluate models for their conceptual soundness with respect to word order, we introduce a new explanation method for sequential data: Order-sensitive Shapley Values (OSV). We conduct an extensive empirical evaluation to validate the method and surface how well various deep NLP models learn word order. Using synthetic data, we first show that OSV is more faithful in explaining model behavior than gradient-based methods. Second, applying to the HANS dataset, we discover that the BERT-based NLI model uses only the word occurrences without word orders. Although simple data augmentation improves accuracy on HANS, OSV shows that the augmented model does not fundamentally improve the model's learning of order. Third, we discover that not all sentiment analysis models learn negation properly: some fail to capture the correct syntax of the negation construct. Finally, we show that pretrained language models such as BERT may rely on the absolute positions of subject words to learn long-range Subject-Verb Agreement. With each NLP task, we also demonstrate how OSV can be leveraged to generate adversarial examples.
