Title :
OMEX: Software for Mining Mathematical Expression Semantics from Scientific Documents
Author :
Stathopoulos, Yiannos A. ; Harrington, Brian
Author_Institution :
Dept. of Comput. Sci., Univ. of Oxford, Oxford, UK
Abstract :
Semantic analysis of scientific documents can benefit from the information carried by mathematical expressions. However, making established data-mining techniques formula-aware is pre-conditioned on the ability to process expressions in documents. In this work, we present OMEX, a software framework capable of extracting mathematical expressions from scientific documents produced using the LATEX typesetting environment.
Keywords :
data mining; mathematics computing; LATEX typesetting environment; OMEX; data mining technique; mathematical expression semantics; scientific document; Lakes; Optical character recognition software; Pipelines; Portable document format; Semantics; Text analysis; data; expression; mathematical; mining; recognition;
Conference_Titel :
Semantic Computing (ICSC), 2011 Fifth IEEE International Conference on
Conference_Location :
Palo Alto, CA
Print_ISBN :
978-1-4577-1648-5
Electronic_ISBN :
978-0-7695-4492-2
DOI :
10.1109/ICSC.2011.65
