Ontology guided knowledge graph improves evidence retrieval for indian knowledge systems
Ontology-Guided Knowledge Graph Construction and Robust Evidence Retrieval for Indian Knowledge Systems
Information Retrieval
Summary
Finding accurate information from Indian Knowledge Systems is tricky because names and meanings can vary a lot. The authors created a special method combining an ontology-based knowledge graph with other search tools to connect information accurately to its original text. They tested several configurations and found their knowledge graph method gave more precise early results, especially for complicated questions. However, it took longer to retrieve data compared to simpler methods, so the choice depends on what matters more: speed, accuracy, or completeness.
What this means in practice
- •For digital librarians: Enhance search systems to retrieve precise multi-step evidence from Indian Knowledge System texts despite ambiguous names and language variations.
- •For law firms: Improve document retrieval in legal cases involving Indian cultural or historical texts where transliteration and related concepts span multiple passages.
Authors
Anand Kaniyaar Sriranga Prasad, Avinash Holenarasipur Nagendra, Mohan Raghavan
Abstract
Retrieving evidence from Indian Knowledge Systems is complicated by transliteration variants, ambiguous names, and relations distributed across passages. We present an ontology-guided knowledge graph (KG) pipeline that links typed entities and relations extracted with Qwen3-32B to original textual evidence. Retrieval combines sense-aware grounding, bounded graph traversal, lexical anchors, relationship-vector search, and passage reranking. We evaluate KG alone, single-vector retrieval (SV), and KG unions with SV and Entity Notes on 320 questions from Dhara Bench, matching the per-question candidate count across internal systems under BGE and Qwen rerankers. Standalone KG has the highest Precision@5 under both rerankers and the highest MRR@20 in Counting, Composite, and Multi-hop among the evaluated internal configurations. With Qwen, KG achieves Multi-hop MRR@20 of 0.8722, compared with 0.7622 for the fully reranked KG + SV union. The KG + SV + Entity Notes union instead provides the highest overall Recall@20 (0.5134), compared with 0.4347 for KG. On the 15 Multi-hop questions, Qwen KG achieves complete-evidence MRR@20 of 0.4651 versus 0.3372 for SV, while both full unions complete ten questions within twenty results compared with nine for KG. Gemini 3.7 Flash, evaluated through manually reviewed source mappings, re mains stronger on overall MRR and nDCG, while internal systems have category-specific advantages. All comparisons are descriptive. A separate deployment timing study measures mean retrieval times of 20.374 s for KG and 0.646 s for SV. The findings support selecting KG or its unions according to the required balance of early relevance, evidence completeness, and retrieval cost.