Affiliation:
1. Department of Computer Science, University of Manchester, UK. jordan.meadows@postgrad.manchester.ac.uk
2. Department of Computer Science, University of Manchester, UK
3. Idiap Research Institute, Switzerland. andre.freitas@idiap.ch
Abstract
Abstract
Automating discovery in mathematics and science will require sophisticated methods of information extraction and abstract reasoning, including models that can convincingly process relationships between mathematical elements and natural language, to produce problem solutions of real-world value. We analyze mathematical language processing methods across five strategic sub-areas (identifier-definition extraction, formula retrieval, natural language premise selection, math word problem solving, and informal theorem proving) from recent years, highlighting prevailing methodologies, existing limitations, overarching trends, and promising avenues for future research.
Subject
Artificial Intelligence,Computer Science Applications,Linguistics and Language,Human-Computer Interaction,Communication
Reference142 articles.
1. Ntcir-11 math-2 task overview;Aizawa,2014
2. Multilingual aliasing for auto-generating proposition banks;Akbik,2016
3. Premise selection for mathematics by corpus analysis and kernel methods;Alama;Journal of Automated Reasoning,2014
4. Mathalign: Linking formula identifiers to their contextual natural language descriptions;Alexeeva,2020
5. Origins of the brain networks for advanced mathematics in expert mathematicians;Amalric;Proceedings of the National Academy of Sciences,2016
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. MaugVLink: Augmenting Mathematical Formulas with Visual Links;2024 IEEE 17th Pacific Visualization Conference (PacificVis);2024-04-23
2. Mathematics, word problems, common sense, and artificial intelligence;Bulletin of the American Mathematical Society;2024-02-15