Auditing Deep Learning processes through Kernel-based Explanatory Models
By Danilo Croce, Daniele Rossini, Roberto Basili. 2019
26 citations recorded by the source corpus.
While NLP systems become more pervasive, their accountability gains value as a focal point of effort. Epistemological opaqueness of nonlinear learning methods, such as deep learning models, can be a major drawback for their adoptions. In this paper, we discuss the application of Layerwise Relevance Propagation over a linguistically motivated neural architecture, the Kernel-based Deep Architecture, in order to trace back connections between linguistic properties of input instances and system decisions. Such connections then guide the construction of argumentations on network’s inferences, i.e., explanations based on real examples, semantically related to the input. We propose here a methodology to evaluate the transparency and coherence of analogy-based explanations modeling an audit stage for the system. Quantitative analysis on two semantic tasks, i.e., question classification and semantic role labeling, show that the explanatory capabilities (native in KDAs) are effective and they pave the way to more complex argumentation methods.
Subfields: Artificial Intelligence, Information Systems and Management, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Kun Qian
- Ban Kawas
- Marina Danilevsky
- Leonardo Ranaldi
- Andrea Santilli
- Yannis Katsis
- Fabio Massimo Zanzotto
- Francesca Fallucchi
In Safety, Robustness & Interpretability
Citations in the corpus
- A Survey of the State of Explainable AI for Natural Language Processing (2020, methodology): “…natural language explanation for a QA system (Abujabal et al., 2017). tion techniques, such as using raw examples to present example-driven approaches (Jiang et al., 2019; Croce et al., 2019) (e.g., Figure 1e), and dependency parse trees to represent input questions (Abujabal et al., 2017).”
- KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations (2020, methodology): “LRP has already been used in the context of explaining decisions in natural language processing tasks (Croce et al., 2019b,a).”