Cutting-edge Tutorial: Machine Reasoning: Technology, Dilemma and Future

摘要

Machine reasoning research aims to build inter-pretable AI systems that can solve problems or draw conclusions from what they are told (i.e. facts and observations) and already know (i.e. models, common sense and knowledge) under certain constraints. Although its "formal" definitions vary in different publications (McCarthy, 1958; Pearl, 1988; Khardon and Roth, 1994; Bottou, 2011; Ben-gio, 2019), machine reasoning methods usually share some commonalities. First, such systems are based on different types of knowledge, such as logical rules, knowledge graphs, common sense, text evidence, etc. Second, such systems use different inference algorithms to manipulate available knowledge for problem-solving. Third, such systems have good interpretability to the predictions. The developments of machine reasoning systems go through several stages. Symbolic reasoning methods represent knowledge using symbolic logic (e.g., propositional logic and first order logic) and perform inference using algorithms such as truth-table approach, inference rules approach, resolution, forward chaining and backward chaining. A major defect is that such methods cannot handle the uncertainty in data. Probabilistic reasoning methods combine probability and symbolic logic into a unified model. Such methods can deal with uncertainty, but suffer the combinatorial explosion when searching in a large discrete symbolic space. With the rapid developments of deep learning, neural reasoning methods attract much attention. Neural-symbolic reasoning methods represent knowledge symbols (such as entities, relationships, actions, logical functions and formulas) as vector or tensor representations, and allow the model to perform end-to-end learning effectively as all components are differentiable. Neural-evidence reasoning methods allow the model to communicate with the environment to acquire evidence for reasoning. As such models assume the reasoning layer is not required to be logical, both structured and unstructured data can be used as knowledge. Besides, as the interaction with the environment can be conducted multiple times, such approaches are good at solving sequential decision-making problems.