Semi-Lexical Languages -- A Formal Basis for Unifying Machine Learning and Symbolic Reasoning in Computer Vision
This addresses the limitation in computer vision where machine learning lacks reasoning frameworks for complex scenarios, potentially improving interpretation tasks.
The paper tackles the problem of interpreting complex visual scenarios by proposing semi-lexical languages as a formal basis to unify machine learning for handling imprecision and symbolic reasoning for domain knowledge, with case studies showing advantages over pure methods.
Human vision is able to compensate imperfections in sensory inputs from the real world by reasoning based on prior knowledge about the world. Machine learning has had a significant impact on computer vision due to its inherent ability in handling imprecision, but the absence of a reasoning framework based on domain knowledge limits its ability to interpret complex scenarios. We propose semi-lexical languages as a formal basis for dealing with imperfect tokens provided by the real world. The power of machine learning is used to map the imperfect tokens into the alphabet of the language and symbolic reasoning is used to determine the membership of input in the language. Semi-lexical languages also have bindings that prevent the variations in which a semi-lexical token is interpreted in different parts of the input, thereby leaning on deduction to enhance the quality of recognition of individual tokens. We present case studies that demonstrate the advantage of using such a framework over pure machine learning and pure symbolic methods.