CCKS 2022 - Evaluation Track 7th China Conference on Knowledge Graph and Semantic Computing Evaluations, CCKS 2022, Qinhuangdao, China, August 24–27, 2022, Revised Selected Papers

This book constitutes the refereed proceedings of the 7th China Conference on Knowledge Graph and Semantic Computing Evaluations, CCKS 2022, which took place in Qinhuangdao, China, in August 2022. 

The 25 full papers presented in this volume were carefully reviewed and selected from 42 submissions. CCKS technology evaluation track aims to provide researchers with platforms and resources for testing knowledge and semantic computing technologies, algorithms and systems, promote the technical development in the field of domestic knowledge, and the integration of academic achievements and industrial needs.

ensemble learning.- Diagram Question Answering with Joint Training and Bottom-Up and Top-Down Attention.- Element Information Enhancement for Diagram Question Answering with Synthetic Data.- Financial Event Extraction of NEC Dataset based on Pointer Network.- High Quality Article Recognition Based On Ernie AndKnowledge Mapping.- High-Quality Article Classification Based on Named Entities of Knowledge Graph and Multi-Head Attention.- Implementation and Optimization of Graph Computing Algorithms based on Graph Database.- Knowledge Graph Construction for Foreign Military Unmanned Systems.- Knowledge-Enhanced Classification: A Scheme for Identification of High-Quality Articles.- Learning Seq2Seq Model with Dynamic Schema Linking for NL2SQL.- Learning to Answer Complex Visual Questions from Multi-View Analysis.- A Prompt-based UIE Framework.- Multi-Modal Representation Learning with Self-Adaptive Threshold for Commodity Verification.- Multimodal Representation Learning-based Product Matching.- Relation Extraction as Text Matching: A Scheme for Multi-hop Knowledge Base Question Answering.- Research on salient reasoning for commonsense knowledge.- Retrieval-Then-Parsing: A Two-Stage Model for SQL Generationin Financial Domain.- Structured design solves multiple tables of NL2SQL.- The Method for Plausibility Evaluation of Knowledge Triple based on QA.