PaperAgent
PaperAgent
Dec 18, 2025 · Artificial Intelligence

Can Ontology‑Aware KG‑RAG Double Table QA Performance on Industrial Standards?

This article presents an ontology‑aware knowledge‑graph RAG framework that transforms complex, hierarchical industrial standard documents into a graph of sections, atomic propositions, and refined triples, achieving nearly double F1 scores on table‑based QA tasks and robust performance on long documents.

LLMOntologyRAG
0 likes · 6 min read
Can Ontology‑Aware KG‑RAG Double Table QA Performance on Industrial Standards?
NetEase Smart Enterprise Tech+
NetEase Smart Enterprise Tech+
Nov 11, 2021 · Artificial Intelligence

Transforming B2B Customer Service: Table QA via Multi‑Turn Dialogue

This article explores how table‑based question answering can be integrated into B2B intelligent customer service by converting table queries into entity‑attribute recognition and multi‑turn dialogue, comparing end‑to‑end NL2SQL and slot‑filling approaches, and presenting NetEase Qiyu's practical implementation with its benefits and use cases.

NL2SQLNLPattribute extraction
0 likes · 10 min read
Transforming B2B Customer Service: Table QA via Multi‑Turn Dialogue