Semantification of Identifiers in Mathematics for Better Math Information Retrieval

Schubotz, Moritz; Grigor’ev, A. V.; Leich, Marcus; Cohl, Howard S.; Meuschke, Norman; Gipp, Béla; Youssef, Abdou; Markl, Volker

doi:10.1145/2911451.2911503

Cited by 51 publications

(75 citation statements)

References 30 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 perform different extraction tasks (extracting identifier definitions [9,13] vs. extracting formulae descriptions [7]) using different datasets (Wikipedia articles [9,13] vs. scientific publications [7]), which so far prevented a comparison of the reported precision an recall values.…”

Section: Methodsmentioning

confidence: 99%

“…To enable comparative performance evaluations for these and other extraction approaches, we created an open evaluation framework by extending the open source MLP and MIR framework Mathosphere introduced in [13]. Section 3.1 presents the evaluation framework and explains major improvements we made to Mathosphere's MLP pipeline.…”

Section: Methodsmentioning

confidence: 99%

“…This Section briefly reviews the following approaches to mathematical identifier definition extraction: (1) the statistical feature analysis of Schubotz et al [13] (Sect. 2.1), (2) the pattern matching approach of Pagel et al [9] (Sect.…”

Section: Related Workmentioning

confidence: 99%

“…Schubotz et al [13] proposed a mathematical language processing (MLP) pipeline and demonstrated the application of the pipeline for extracting the definiens of identifiers in formulae contained in Wikipedia. In summary, the MLP pipeline includes the following steps:…”

Section: Statistical Feature Analysis (St)mentioning

confidence: 99%

“…Schubotz et al report a precision of p = .207 and a recall of r = .284 for extracting identifier definitions [13]. The weighting parameters, the Gaussians and the threshold for the overall score must be manually adjusted to the specific use case, which can be a tedious process.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Evaluating and Improving the Extraction of Mathematical Identifier Definitions

Schubotz

Krämer

Meuschke

et al. 2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Mathematical formulae in academic texts significantly contribute to the overall semantic content of such texts, especially in the fields of Science, Technology, Engineering and Mathematics. Knowing the definitions of the identifiers in mathematical formulae is essential to understand the semantics of the formulae. Similar to the sense-making process of human readers, mathematical information retrieval systems can analyze the text that surrounds formulae to extract the definitions of identifiers occurring in the formulae. Several approaches for extracting the definitions of mathematical identifiers from documents have been proposed in recent years. So far, these approaches have been evaluated using different collections and gold standard datasets, which prevented comparative performance assessments. To facilitate future research on the task of identifier definition extraction, we make three contributions. First, we provide an automated evaluation framework, which uses the dataset and gold standard of the NTCIR-11 Math Retrieval Wikipedia task. Second, we compare existing identifier extraction approaches using the developed evaluation framework. Third, we present a new identifier extraction approach that uses machine learning to combine the wellperforming features of previous approaches. The new approach increases the precision of extracting identifier definitions from 17.85% to 48.60%, and increases the recall from 22.58% to 28.06%. The evaluation framework, the dataset and our source code are openly available at: https:// ident.formulasearchengine.com.

show abstract