1 views collected around this technical thread.
The CCKS 2021 competition invites researchers to develop Chinese Knowledge Base Question Answering systems that leverage a life‑service knowledge graph from Meituan, offering detailed task description, dataset information, registration procedures, timelines, and prize incentives.
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.
This article presents an in‑depth overview of Alibaba's Xiaomì conversational AI system, describing how structured knowledge—including FAQs, phrase‑based knowledge, knowledge graphs, and machine‑read documents—is organized into a two‑level schema and applied to knowledge‑based QA (KBQA) and event‑based QA (EBQA) with detailed model pipelines, ranking, type inference, and recommendation techniques, while also discussing practical challenges and future directions.