analiza aiqbench
The paper proposes GHTM, a topic model for Bengali that combines TF-IDF, GloVe embeddings, and a graph convolutional network, then factorizes the resulting representations to extract topics. Its reported gains are modest (NPMI of 0.27 to 0.28) and rest on benchmarks across three datasets plus a new textbook-based corpus, NCTBText. For readers, the practical takeaway is a lightweight alternative to heavy neural topic models for a low-resource language, with the caveat that the evidence is limited to the authors' own benchmarks.
GHTM: A graph-based hybrid topic modeling approach for Bengali language
arXiv:2508.00605v3 Announce Type: replace Abstract: Topic modeling is a natural language processing technique used to discover latent themes and abstract topics from text corpora by grouping co-occurring keywords. Although widely researched in English, topic modeling remains understudied in Bengali due to a lack of adequate resources and initiatives. Existing Bengali topic modeling research lacks exploration of modern methodological approaches, reproducible implementations, diverse datasets, and systematic benchmarking. To bridge these gaps, this study presents Graph-based Hybrid Topic Model (GHTM), a novel architecture that synthesizes the distinct strengths of multiple paradigms by unifying statistical (TF-IDF), semantic (GloVe), and structural (GCN) modalities to construct semantically aligned document representations. GHTM later employs matrix factorization for topic extraction, offering a computationally lightweight alternative to resource-intensive neural and graph-based approaches. Through comprehensive benchmarking across three Bengali datasets of varying scales, GHTM consistently surpasses both traditional and contemporary topic modeling approaches, achieving improved topic coherence (NPMI: 0.27-0.28) and high topic diversity while maintaining computational efficiency. The model also outperformed established graph-based models on the English 20Newsgroups benchmark. Additionally, we introduce NCTBText, a diverse Bengali textbook-based dataset comprising 8,650 text documents, providing much-needed topical diversity beyond newspaper-centric Bengali corpora.
Abstract:Topic modeling is a natural language processing technique used to discover latent themes and abstract topics from text corpora by grouping co-occurring keywords. Although widely researched in English, topic modeling remains understudied in Bengali due to a lack of adequate resources and initiatives. Existing Bengali topic modeling research lacks exploration of modern methodological approaches, reproducible implementations, diverse datasets, and systematic benchmarking. To bridge these gaps, this study presents Graph-based Hybrid Topic Model (GHTM), a novel architecture that synthesizes the distinct strengths of multiple paradigms by unifying statistical (TF-IDF), semantic (GloVe), and structural (GCN) modalities to construct semantically aligned document representations. GHTM later employs matrix factorization for topic extraction, offering a computationally lightweight alternative to resource-intensive neural and graph-based approaches. Through comprehensive benchmarking across three Bengali datasets of varying scales, GHTM consistently surpasses both traditional and contemporary topic modeling approaches, achieving improved topic coherence (NPMI: 0.27-0.28) and high topic diversity while maintaining computational efficiency. The model also outperformed established graph-based models on the English 20Newsgroups benchmark. Additionally, we introduce NCTBText, a diverse Bengali textbook-based dataset comprising 8,650 text documents, providing much-needed topical diversity beyond newspaper-centric Bengali corpora.
Computation and Language (cs.CL)
arXiv:2508.00605 [cs.CL]
(or arXiv:2508.00605v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2508.00605 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 279 cuvinte
Subiecte conexe
Presentation: Engineering AI for Creativity and Curiosity on Mobile
InfoQ · 21 iul. 2026
Building trade assistant: How Jefferies optimized front office trading operations with AI
AWS · 23 iul. 2026
Corey O’Meara (E.ON): Finding Real Quantum Advantage in Grid Optimization
The Quantum Insider · 10 oct. 2026
Microsoft’s AI chief says superintelligence is near, but won’t take your job
The Verge · 8 iun. 2026