Жеткіліктілік

AbstractIn this paper, we propose a new task for assessing the quality of natural language arguments. The premises of a well-reasoned argument should provide enough evidence for accepting or rejecting …...

AbstractThe paper presents a novel discourse-based approach to argument quality assessment defined as a graph classification task, where the depth of reasoning (argumentation) is evident from the number and type …...

AbstractInterpretable methods to reveal the internal reasoning processes behind machine learning models have attracted increasing attention in recent years. To quantify the extent to which the identified interpretations truly reflect …...

AbstractRecent work in Natural Language Processing has focused on developing approaches that extract faithful explanations, either via identifying the most important tokens in the input (i.e. post-hoc explanations) or by …...

AbstractFeature attribution methods (FAs) are popular approaches for providing insights into the model reasoning process of making predictions. The more faithful a FA is, the more accurately it reflects which …...

AbstractFeature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency. In this paper, we highlight an intriguing property …...