Discovery and recognition of formula concepts using machine learning
Bibliographic Data
| ID | 21441713 |
|---|---|
| Authors | Philipp Scharpf (0000-0002-4212-0508, University of Konstanz), Moritz Schubotz (0000-0001-7141-4997, FIZ Karlsruhe – Leibniz Institute for Information Infrastructure), Howard S Cohl (0000-0002-9398-455X, National Institute of Standards and Technology), Corinna Breitinger (0000-0001-6586-0392, University of Göttingen), Bela Gipp (0000-0001-6522-3019, University of Göttingen, corresponding author) |
| Year | 2023 |
| Volume | 128 |
| Issue | 9 |
| Pages | 4971-5025 |
| Publication date | 2023-09-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Scientometrics (JOURNAL) |
| Journal identifiers | ISSN: 0138-9130 • E-ISSN: 1588-2861 |
| Publisher | Springer Science and Business Media LLC (PUBLISHER) |
| DOI | 10.1007/s11192-023-04667-9 |
| OpenAlex | W4384201826 |
| Language | EN |
| References cited | 31 |
Citation-based Information Retrieval (IR) methods for scientific documents have proven effective for IR applications, such as Plagiarism Detection or Literature Recommender Systems in academic disciplines that use many references. In science, technology, engineering, and mathematics, researchers often employ mathematical concepts through formula notation to refer to prior knowledge. Our long-term goal is to generalize citation-based IR methods and apply this generalized method to both classical references and mathematical concepts. In this paper, we suggest how mathematical formulas could be cited and define a Formula Concept Retrieval task with two subtasks: Formula Concept Discovery (FCD) and Formula Concept Recognition (FCR). While FCD aims at the definition and exploration of a ‘Formula Concept’ that names bundled equivalent representations of a formula, FCR is designed to match a given formula to a prior assigned unique mathematical concept identifier. We present machine learning-based approaches to address the FCD and FCR tasks. We then evaluate these approaches on a standardized test collection (NTCIR arXiv dataset). Our FCD approach yields a precision of 68% for retrieving equivalent representations of frequent formulas and a recall of 72% for extracting the formula name from the surrounding text. FCD and FCR enable the citation of formulas within mathematical documents and facilitate semantic search and question answering, as well as document similarity assessments for plagiarism detection or recommender systems
Arithmetic · Citation · Identifier · Information retrieval · Mathematical notation · Notation · Similarity (geometry) · Task (project management) · World Wide Web · Advanced Text Analysis Techniques · Artificial Intelligence · Computer Science · Mathematics · Mathematics, Computing, and Information Processing · Natural Language Processing Techniques
| Highly cited | No |
|---|