AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific Formulas

Arun Josephraj Arokiaraj, Samah Ibrahim, André Then, Bashar Ibrahim () and Stephan Peter ()
Additional contact information
Arun Josephraj Arokiaraj: Department of Basic Sciences, Ernst-Abbe University of Applied Sciences Jena, Carl-Zeiss-Promenade 2, 07745 Jena, Germany
Samah Ibrahim: Department of Computer Science, Gulf University for Science and Technology, Hawally 32093, Kuwait
André Then: Department of Mathematics and Computer Science, Friedrich Schiller University Jena, Fürstengraben, 07743 Jena, Germany
Bashar Ibrahim: Department of Mathematics and Computer Science, Friedrich Schiller University Jena, Fürstengraben, 07743 Jena, Germany
Stephan Peter: Department of Basic Sciences, Ernst-Abbe University of Applied Sciences Jena, Carl-Zeiss-Promenade 2, 07745 Jena, Germany

Mathematics, 2025, vol. 13, issue 14, 1-27

Abstract: The Adaptive Skip-gram (AdaGram) algorithm extends traditional word embeddings by learning multiple vector representations per word, enabling the capture of contextual meanings and polysemy. Originally implemented in Julia, AdaGram has seen limited adoption due to ecosystem fragmentation and the comparative scarcity of Julia’s machine learning tooling compared to Python’s mature frameworks. In this work, we present a Python-based reimplementation of AdaGram that facilitates broader integration with modern machine learning tools. Our implementation expands the model’s applicability beyond natural language, enabling the analysis of scientific notation—particularly chemical and physical formulas encoded in LaTeX. We detail the algorithmic foundations, preprocessing pipeline, and hyperparameter configurations needed for interdisciplinary corpora. Evaluations on real-world texts and LaTeX-encoded formulas demonstrate AdaGram’s effectiveness in unsupervised word sense disambiguation. Comparative analyses highlight the importance of corpus design and parameter tuning. This implementation opens new applications in formula-aware literature search engines, ambiguity reduction in automated scientific summarization, and cross-disciplinary concept alignment.

Keywords: AdaGram; word sense disambiguation; scientific formula analysis; semantic relationships; natural language processing; information retrieval (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/14/2241/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/14/2241/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:14:p:2241-:d:1699129

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().