To improve the explainability of leading Transformer networks used in NLP, it is important to tease apart genuine symbolic rules from merely associative input-output patterns. However, we identify several inconsistencies in how ``symbolicity'' has been construed in recent NLP literature. To mitigate this problem, we propose two criteria to be the most relevant, one pertaining to a system's internal architecture and the other to the dissociation between abstract rules and specific input identities. From this perspective, we critically examine prior work on the symbolic capacities of Transformers, and deem the results to be fundamentally inconclusive for reasons inherent in experiment design. We further maintain that there is no simple fix to this problem, since it arises -- to an extent -- in all end-to-end settings. Nonetheless, we emphasize the need for more robust evaluation of whether non-symbolic explanations exist for success in seemingly symbolic tasks. To facilitate this, we experiment on four sequence modelling tasks on the T5 Transformer in two experiment settings: zero-shot generalization, and generalization across class-specific vocabularies flipped between the training and test set. We observe that T5's generalization is markedly stronger in sequence-to-sequence tasks than in comparable classification tasks. Based on this, we propose a thus far overlooked analysis, where the Transformer itself does not need to be symbolic to be part of a symbolic architecture as the processor, operating on the input and output as external memory components.

翻译：为提升自然语言处理领域主流Transformer网络的可解释性，区分真正的符号规则与简单的关联性输入-输出模式至关重要。然而，我们发现近期自然语言处理文献中对"符号性"的界定存在若干不一致之处。针对此问题，我们提出两个最具相关性的标准：一个涉及系统内部架构，另一个涉及抽象规则与特定输入身份之间的分离。基于这一视角，我们批判性地审视了先前关于Transformer符号能力的研究，认为其结论因实验设计固有缺陷而根本不可证伪。我们进一步主张这个问题不存在简单解决方案——因为它在某种程度上存在于所有端到端设定中。尽管如此，我们强调需要更稳健地评估看似符号任务的成功是否可能存在非符号解释。为此，我们在T5 Transformer上以两种实验设置（零样本泛化与训练测试集间类别特定词汇翻转泛化）对四个序列建模任务进行实验。我们观察到T5在序列到序列任务中的泛化能力显著强于可比分类任务。基于此，我们提出一个迄今被忽视的分析视角：Transformer本身无需是符号系统，即可作为处理器组件参与符号架构——通过将输入输出视为外部存储组件运作。