Neuro-Symbolic Methods for Hybrid Reasoning
Neuro-Symbolic Methods fuse deep learning and symbolic reasoning. I introduce two Neuro-Symbolic methods: NSEdit and Neural Interpretation.
NSEdit (Neuro-Symbolic Edit) is a novel Transformer-based code repair method. Given only the source code that contains bugs, NSEdit predicts an editing sequence that can fix the bugs. The edit grammar is formulated as a regular language, and the Transformer uses it as a neural-symbolic scripting interface to generate editing programs. NSEdit is evaluated on various code repair datasets and achieved a new state-of-the-art accuracy (24.04%24.04%) on the Tufano small dataset of the CodeXGLUE benchmark.
Can a Python program be executed statement-by-statement by neural networks composed according to the source code? We formulate the Neuro-Symbolic Execution Problem and introduce Neural Interpretation (NI), the first neural model for the execution of generic source code that allows missing definitions. NI preserves source code structure, where every variable has a vector encoding, and every function executes a neural network. NI is the first neural model capable of executing Py150 dataset programs, including library functions without concrete inputs, and it can be trained with flexible code understanding objectives.
Committee: Jin Tian (major professor), Hongyang Gao, Ali Jannesari, Hridesh Rajan, and Ryan Martin
Join on WebEx: https://iastate.webex.com/meet/jtian