Automated Classification and Categorization of Mathematical Knowledge

Radim,; ehůřek,; Sojka, Petr

doi:10.1007/978-3-540-85110-3_44

Cited by 45 publications

(59 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We have developed an MSC classifier (guessed MSC) that is able to assign the top-level MSC for the retro-digitized articles. Our results convincingly demonstrate the feasibility of a machine learning approach to the classification of mathematical papers [25].…”

Section: Mathematical Document Classification and Categorizationsupporting

confidence: 66%

“…Terminology evolved and understanding certain expressions requires reading and understanding the whole paper in the context of its time. Help is at hand in the guise of MSC codes suggested by an automated classifier trained via machine learning techniques from a database of articles already classified [39,25].…”

Section: Handling Metadatamentioning

confidence: 99%

“…web-based Metadata Editor [2], 4. tools for classifying mathematical documents and measuring their similarity [25]; 5. workflow for born-digital publication production with direct export of metadata for DML [27];…”

mentioning

confidence: 99%

See 2 more Smart Citations

Document engineering for a digital library

Sojka

Hatlapatka

2010

Proceedings of the 10th ACM Symposium on Document Engineering

Self Cite

View full text Add to dashboard Cite

This paper describes several innovative document transformations and tools that have been developed in the process of building the Digital Mathematical Library DML-CZ http://dml.cz. The main result presented in this paper is our PDF re-compression tool, developed using a jbig2enc library. Together with other programs, especially pdfsizeopt.py by Péter Szabó, we have managed to decrease PDF storage size and transmission needs by 62%: using both programs we reduced the size of the original PDFs to 38%. This paper briefly describes other approaches and tools developed while creating the digital library. The batch digital signature stamper, the document similarity metrics which uses four different methods, a [meta]data validation process and some math OCR tools represent some of the main byproducts of this project. These ways of document engineering, together with Google Scholar indexing optimization, have led to the success of serving digitized and born-digital scientific math documents to the public in DML-CZ, and will be employed also in the project of The European Digital Mathematics Library, EUDML.

show abstract

Section: Mathematical Document Classification and Categorizationsupporting

confidence: 66%

Section: Handling Metadatamentioning

confidence: 99%

See 1 more Smart Citation

Document engineering for a digital library

Sojka

Hatlapatka

2010

Proceedings of the 10th ACM Symposium on Document Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Perhaps the area of mathematical software with the greatest potential for machine learning applications is Mathematical Knowledge Management (MKM) [12] since many of the tasks are similar to Natural Language Processing (NLP) where machine learning has seen extensive use. For example, [35] describes the automatic identification of a suitable top level from the Mathematics Subject Classification (MSC) system for thousands of articles using an SVM; while [29] describes how NLP techniques were adapted to build a part of speech tagger used for key phrase extraction in the database zbMATH.…”

Section: Mathematical Knowledge Managementmentioning

confidence: 99%

Machine Learning for Mathematical Software

England

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

While there has been some discussion on how Symbolic Computation could be used for AI there is little literature on applications in the other direction. However, recent results for quantifier elimination suggest that, given enough example problems, there is scope for machine learning tools like Support Vector Machines to improve the performance of Computer Algebra Systems. We survey the authors own work and similar applications for other mathematical software. It may seem that the inherently probabilistic nature of machine learning tools would invalidate the exact results prized by mathematical software. However, algorithms and implementations often come with a range of choices which have no effect on the mathematical correctness of the end result but a great effect on the resources required to find it, and thus here, machine learning can have a significant impact.

show abstract

“…Examples of such services include the Citation Service, responsible for citation resolving and indexing or Similarity Service [26,27], which would be able to return similar objects based on a predefined metrics and criteria. Similarly, additional extension services are hoped to be developed in the future by third parties or by the involved partners.…”

Section: Extensionsmentioning

confidence: 99%