New GRISP method uses SLM for SPARQL question answering over knowledge graphs

Researchers have developed GRISP, a new method for question answering over knowledge graphs using a fine-tuned small language model (SLM). GRISP generates a SPARQL query skeleton from natural language questions and then resolves placeholders by searching and re-ranking knowledge graph items. The SLM is trained on data generated from question-query pairs, and the method has shown improved results on Wikidata and Freebase benchmarks compared to other fine-tuning approaches. AI

IMPACT This research could improve the efficiency and accuracy of querying structured data using natural language, potentially benefiting applications that rely on knowledge graphs.

RANK_REASON The cluster contains a research paper detailing a novel method for question answering over knowledge graphs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• Freebase
• Hugging Face
• knowledge graph
• Sebastian Walter
• small language model
• SPARQL
• Wikidata

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →