Automating discovery in mathematics and science will require sophisticated methods of
information extraction and abstract reasoning, including models that can convincingly …

Mathematical formulae are essential in science, but face challenges of ambiguity, due to the
use of a small number of identifiers to represent an immense number of concepts …

Word embedding, which represents individual words with semantically fixed-length vectors,
has made it possible to successfully apply deep learning to natural language processing …

Wikipedia combines the power of AI solutions and human reviewers to safeguard article
quality. Quality control objectives include detecting malicious edits, fixing typos, and spotting …

Informal mathematical text underpins real-world quantitative reasoning and communication.
Developing sophisticated methods of retrieval and abstraction from this dual modality is …

A Survey on Retrieval of Mathematical Knowledge Page 1 Math.Comput.Sci. (2016) 10:409–427
DOI 10.1007/s11786-016-0274-0 Mathematics in Computer Science A Survey on Retrieval of …

Natural language models often fall short when understanding and generating mathematical
notation. What is not clear is whether these shortcomings are due to fundamental limitations …

Mathematical concepts and formulations play a fundamental role in many scientific domains.
As such, the use of mathematical expressions represents a promising method of interlinking …

Current mathematical search systems allow math expressions within a document to be
queried using math expressions and keywords. To accept such queries, math search …

Nearly all of the recent mathematical literature, and much of the old literature, are online and
mostly in natural-language form. Therefore, math content processing presents some of the …