A. S. Girsang

Structured Entity and Relation Extraction from Sequential Multimodal Audio-Video Content Using Large Language Models

The rapid growth of digital media has increased the availability of posts that combine spoken narration, visual demonstrations, embedded images, captions, and video sequences within a single communicative unit. Although existing information extraction systems perform well on textual data, their effectiveness remains li...

Named Entity Recognition for Location Prediction Traffic Accident based on Twitter Data

Automatic Text Summarization of Indonesian Text with Contextual Top2Vec

A Reproducible and Adaptive Metadata-Aware Text-to-SQL System Using Small Language Models for Resource-Constrained Self-Service BI

Temporal-spatial reasoning over hypergraph knowledge structures for multimodal retrieval-augmented generation

Results support hypergraph-native traversal with temporal-spatial-aware scoring as an effective retrieval paradigm for the evaluated multimodal RAG setting, particularly for constraint-driven queries that semantic-only retrieval cannot address.