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

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 com...

Full description

Saved in:
Bibliographic Details
Main Authors: Arun Josephraj Arokiaraj, Samah Ibrahim, André Then, Bashar Ibrahim, Stephan Peter
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/14/2241
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418354220072960
author Arun Josephraj Arokiaraj
Samah Ibrahim
André Then
Bashar Ibrahim
Stephan Peter
author_facet Arun Josephraj Arokiaraj
Samah Ibrahim
André Then
Bashar Ibrahim
Stephan Peter
author_sort Arun Josephraj Arokiaraj
collection DOAJ
description 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.
format Article
id doaj-art-56c5c1e28a524dbeb83ae9dfdd444ced
institution Kabale University
issn 2227-7390
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-56c5c1e28a524dbeb83ae9dfdd444ced2025-08-20T03:32:27ZengMDPI AGMathematics2227-73902025-07-011314224110.3390/math13142241AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific FormulasArun Josephraj Arokiaraj0Samah Ibrahim1André Then2Bashar Ibrahim3Stephan Peter4Department of Basic Sciences, Ernst-Abbe University of Applied Sciences Jena, Carl-Zeiss-Promenade 2, 07745 Jena, GermanyDepartment of Computer Science, Gulf University for Science and Technology, Hawally 32093, KuwaitDepartment of Mathematics and Computer Science, Friedrich Schiller University Jena, Fürstengraben, 07743 Jena, GermanyDepartment of Mathematics and Computer Science, Friedrich Schiller University Jena, Fürstengraben, 07743 Jena, GermanyDepartment of Basic Sciences, Ernst-Abbe University of Applied Sciences Jena, Carl-Zeiss-Promenade 2, 07745 Jena, GermanyThe 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.https://www.mdpi.com/2227-7390/13/14/2241AdaGramword sense disambiguationscientific formula analysissemantic relationshipsnatural language processinginformation retrieval
spellingShingle Arun Josephraj Arokiaraj
Samah Ibrahim
André Then
Bashar Ibrahim
Stephan Peter
AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific Formulas
Mathematics
AdaGram
word sense disambiguation
scientific formula analysis
semantic relationships
natural language processing
information retrieval
title AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific Formulas
title_full AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific Formulas
title_fullStr AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific Formulas
title_full_unstemmed AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific Formulas
title_short AdaGram in Python: An AI Framework for Multi-Sense Embedding in Text and Scientific Formulas
title_sort adagram in python an ai framework for multi sense embedding in text and scientific formulas
topic AdaGram
word sense disambiguation
scientific formula analysis
semantic relationships
natural language processing
information retrieval
url https://www.mdpi.com/2227-7390/13/14/2241
work_keys_str_mv AT arunjosephrajarokiaraj adagraminpythonanaiframeworkformultisenseembeddingintextandscientificformulas
AT samahibrahim adagraminpythonanaiframeworkformultisenseembeddingintextandscientificformulas
AT andrethen adagraminpythonanaiframeworkformultisenseembeddingintextandscientificformulas
AT basharibrahim adagraminpythonanaiframeworkformultisenseembeddingintextandscientificformulas
AT stephanpeter adagraminpythonanaiframeworkformultisenseembeddingintextandscientificformulas