CALT: A Library for Computer Algebra with Transformer
ACM Communications in Computer Algebra · 01.12.2025 · 59 (4) · 121-128
DOI: 10.1145/3832046.3832059 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Communications in Computer Algebra, online erschienen am 18.08.2026. Verfasst von Hiroshi Kera und 2 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Kera, H., Arakawa, S., & Sato, Y. (2025). CALT: A Library for Computer Algebra with Transformer. ACM Communications in Computer Algebra, 59(4), 121-128. https://doi.org/10.1145/3832046.3832059
Vancouver
Kera H, Arakawa S, Sato Y. CALT: A Library for Computer Algebra with Transformer. ACM Communications in Computer Algebra. 2025;59(4):121-128. doi:10.1145/3832046.3832059
BibTeX
@article{Kera2025,
author = {Kera, Hiroshi and Arakawa, Shun and Sato, Yuta},
title = {CALT: A Library for Computer Algebra with Transformer},
journal = {ACM Communications in Computer Algebra},
year = {2025},
volume = {59},
number = {4},
pages = {121--128},
doi = {10.1145/3832046.3832059}
}
EUVIMED