mlsanityData to 7 Oct 2026

Can Neural Networks Learn Symbolic Rewriting?

arXiv 1911.04873 ↗First posted 7 Nov 2019cs.AI cs.CL cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 1; 2023: 3; 2024: 3; 2025: 2.

12 papers.

  1. 2021Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematicscited by 27
  2. 2022Simplifying Polylogarithms with Machine Learningcited by 14
  3. 2021Analyzing the Nuances of Transformers' Polynomial Simplification Abilitiescited by 9
  4. 2023Alien Codingcited by 9
  5. 2023MizAR 60 for Mizar 50cited by 6
  6. 2021Learning Equational Theorem Provingcited by 5
  7. 2023Generating Elementary Integrable Expressionscited by 4
  8. 2024Symbolic Integration Algorithm Selection with Machine Learning: LSTMs vs Tree LSTMscited by 3
  9. 2025Learning Conjecturing from Scratchcited by 3
  10. 2024The Liouville Generator for Producing Integrable Expressionscited by 2
  11. 2024Transformers to Predict the Applicability of Symbolic Integration Routinescited by 2
  12. 2025Tree-Based Deep Learning for Ranking Symbolic Integration Algorithmscited by 1