Towards a Framework for Evaluating Explanations in Automated Fact Verification
This work addresses the need for interpretability in complex NLP models for researchers and practitioners, but it is incremental as it builds on existing concepts without introducing new methods or data.
The authors tackled the lack of systematic evaluation methods for explanations in automated fact verification by proposing a formal framework to assess rationalizing explanations, resulting in a structured approach tailored to different explanation types from free-form to argumentative.
As deep neural models in NLP become more complex, and as a consequence opaque, the necessity to interpret them becomes greater. A burgeoning interest has emerged in rationalizing explanations to provide short and coherent justifications for predictions. In this position paper, we advocate for a formal framework for key concepts and properties about rationalizing explanations to support their evaluation systematically. We also outline one such formal framework, tailored to rationalizing explanations of increasingly complex structures, from free-form explanations to deductive explanations, to argumentative explanations (with the richest structure). Focusing on the automated fact verification task, we provide illustrations of the use and usefulness of our formalization for evaluating explanations, tailored to their varying structures.