CALT: A Library for Computer Algebra with Transformer
This work addresses the need for accessible tools in the symbolic computation community to leverage deep learning for emulating symbolic computations, though it is incremental as it builds on existing Transformer methods.
The authors introduced CALT, a Python library that enables non-experts to train Transformer models for symbolic computation tasks by providing examples of symbolic expressions, aiming to facilitate research in this area.
Recent advances in artificial intelligence have demonstrated the learnability of symbolic computation through end-to-end deep learning. Given a sufficient number of examples of symbolic expressions before and after the target computation, Transformer models - highly effective learners of sequence-to-sequence functions - can be trained to emulate the computation. This development opens up several intriguing challenges and new research directions, which require active contributions from the symbolic computation community. In this work, we introduce Computer Algebra with Transformer (CALT), a user-friendly Python library designed to help non-experts in deep learning train models for symbolic computation tasks.