On the Readability of Kernel-based Deep Learning Models in Semantic Role Labeling Tasks over Multiple Languages

Abstract

Sentence embeddings are effective input vectors for the neural learning of a number of inferences about content and meaning. Unfortunately, most of such decision processes are epistemologically opaque as for the limited interpretability of the acquired neural models based on the involved embeddings. In this paper, we concentrate on the readability of neural models, discussing an embedding technique (the Nyström methodology) that corresponds to the reconstruction of a sentence in a kernel space, capturing grammatical and lexical semantic information. From this method, we build a Kernel-based Deep Architecture that is characterized by inherently high interpretability properties, as the proposed embedding is derived from examples, i.e., landmarks, that are both human readable and labeled. Its integration with an explanation methodology, the Layer-wise Relevance Propagation, supports here the automatic compilation of argumentations for the Kernel-based Deep Architecture decisions, expressed in form of analogy with activated landmarks. Quantitative evaluation against the Semantic Role Labeling task, both in English and Italian, suggests that explanations based on semantic and syntagmatic structures are rich and characterize convincing arguments, as they effectively help the user in assessing whether or not to trust the machine decisions.