SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.
I was able to train the model as per your instructions. But my ultimate goal is to be able to build a Neuro-Symbolic Reasoning system similar to this Currently I have the "Semantic Parsing" part of the system working. But I still need to get a "Reasoning" part (namely AMR-to-logic and Logical Neural Networks). Any information about them (or links to the repositories) would be greatly appreciated.
I was able to train the model as per your instructions. But my ultimate goal is to be able to build a Neuro-Symbolic Reasoning system similar to this Currently I have the "Semantic Parsing" part of the system working. But I still need to get a "Reasoning" part (namely AMR-to-logic and Logical Neural Networks). Any information about them (or links to the repositories) would be greatly appreciated.