Non-Monotonicity in Probabilistic Reasoning
We start by defining an approach to non-monotonic probabilistic reasoning in terms of non-monotonic categorical (true-false) reasoning. We identify a type of non-monotonic probabilistic reasoning, akin to default inheritance, that is commonly found in practice, especially in "evidential" and "Bayesian" reasoning. We formulate this in terms of the Maximization of Conditional Independence (MCI), and identify a variety of applications for this sort of default. We propose a formalization using Pointwise Circumscription. We compare MCI to Maximum Entropy, another kind of non-monotonic principle, and conclude by raising a number of open questions
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Continuity and Monotonicity of Preferences and Probabilistic Equivalence
We show that probabilistic equivalence of a regret-based preference relationship over random variables is implied by a weak form of continuity and monotonicity.
FormCan neural networks understand monotonicity reasoning?
Monotonicity reasoning is one of the important reasoning skills for any intelligent natural language inference (NLI) model in that it requires the ability to capture the interaction between lexical and syntactic structur…
Data AugmentationNatural Language InferenceAn Axiomatization of the Random Priority Rule
We study the problem of assigning indivisible objects to agents where each is to receive at most one. To ensure fairness in the absence of monetary compensation, we consider random assignments. Random Priority, also know…
FairnessHELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning
Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including tho…
Data AugmentationNatural Language InferenceAttentive Tree-structured Network for Monotonicity Reasoning
Many state-of-art neural models designed for monotonicity reasoning perform poorly on downward inference. To address this shortcoming, we developed an attentive tree-structured neural network. It consists of a tree-based…
Natural Language InferenceSentence