7 papers
Incremental Graph Construction Enables Robust Spectral Clustering of Texts
Marko PranjiÄ, Boshko Koloski, Nada LavraÄ +2
Neighborhood graphs are a critical but often fragile step in spectral clustering of text embeddings. On realistic text datasets, standard -NN graphs can contain many disconnecte…
Recent Advances and Future Directions in Literature-Based Discovery
Andrej Kastrin, Bojan Cestnik, Nada LavraÄ
The explosive growth of scientific publications has created an urgent need for automated methods that facilitate knowledge synthesis and hypothesis generation. Literature-based dis…
From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies
Blaž Škrlj, Boshko Koloski, Senja Pollak +1
Integrating structured knowledge from Knowledge Graphs (KGs) into Large Language Models (LLMs) enhances factual grounding and reasoning capabilities. This survey paper systematical…
Extracting domain-specific terms using contextual word embeddings
Andraž Repar, Nada LavraÄ, Senja Pollak
Automated terminology extraction refers to the task of extracting meaningful terms from domain-specific texts. This paper proposes a novel machine learning approach to terminology…
Make Literature-Based Discovery Great Again through Reproducible Pipelines
Bojan Cestnik, Andrej Kastrin, Boshko Koloski +1
By connecting disparate sources of scientific literature, literature\-/based discovery (LBD) methods help to uncover new knowledge and generate new research hypotheses that cannot…
HorNets: Learning from Discrete and Continuous Signals with Routing Neural Networks
Boshko Koloski, Nada LavraÄ, Blaž Å krlj
Construction of neural network architectures suitable for learning from both continuous and discrete tabular data is a challenging research endeavor. Contemporary high-dimensional…