Tencent Cloud Developer
Nov 20, 2020 · Artificial Intelligence
Design of a Symbolic Evaluation Set for Knowledge Question Answering (KBQA)
The paper introduces a symbolic‑logic‑focused evaluation set for knowledge‑base question answering, defining single, deterministic, and non‑deterministic element symbols with linguistic tags, constructing complex celebrity‑domain queries, and showing that current commercial KBQA systems achieve only modest accuracy, highlighting the need for more robust reasoning capabilities.
AIKBQAevaluation dataset
0 likes · 11 min read