Can Neural Networks Learn Symbolic Rewriting?
This addresses the problem of automating symbolic reasoning for researchers in AI and mathematics, but it is incremental as it builds on existing neural methods without major breakthroughs.
The paper investigates whether current neural architectures can learn symbolic rewriting, using datasets from automated proofs and synthetic polynomial terms, and finds that neural machine translation models show some capability but with limitations.
This work investigates if the current neural architectures are adequate for learning symbolic rewriting. Two kinds of data sets are proposed for this research -- one based on automated proofs and the other being a synthetic set of polynomial terms. The experiments with use of the current neural machine translation models are performed and its results are discussed. Ideas for extending this line of research are proposed, and its relevance is motivated.