A Survey in Mathematical Language Processing
This is an incremental survey for researchers in AI and mathematics, summarizing existing work without new results.
The paper surveys recent developments in mathematical language processing, tracking approaches across five sub-areas to highlight successful methods and limitations.
Informal mathematical text underpins real-world quantitative reasoning and communication. Developing sophisticated methods of retrieval and abstraction from this dual modality is crucial in the pursuit of the vision of automating discovery in quantitative science and mathematics. We track the development of informal mathematical language processing approaches across five strategic sub-areas in recent years, highlighting the prevailing successful methodological elements along with existing limitations.