This volume contains the papers of evaluation tasks presented at the China Conference on Knowledge Graph and Semantic Computing (CCKS 2018). CCKS 2018 is the premier forum on Knowledge Graph and Semantic Technologies for Chinese researchers and practitioners from academia, industry, and government. It covers wider fields including the Knowledge Graph, the Semantic Web, Linked Data, NLP, knowledge representation, graph databases etc. CCKS is organized by the Technical Committee on Language and Knowledge Computing of CIPS (Chinese Information Processing Society of China). CCKS 2018 has hosted four evaluation tasks: (1) Clinical Named Entity Recognition. Given a set of digital medical records in plain text, this task is to recognize entity mentions in medical domain, and classify them into pre-defined categories, such as disease, symptom, etc. (2) Command Understanding over the music domain. Given a set of command in natural language, it is required to identify whether they ask for music, and find the corresponding arguments. (3) Customer Service Question Matching. Given a set of question pairs in natural language, it is required to identify whether they have equivalent semantic. (4) Chinese Open-domain Question Answering. Given a set of questions in natural language, it is required to answer them according to a given knowledge base. The four evaluation tasks have involved many participants coming from universities, companies and research institutes. They have involved 288 participants, and 247 of them submitted their final results. We invited all the participants to submit a research paper describing their methods and we received 22 submissions. Each of the submissions went through a thorough peer review process, and 15 papers were accepted for the presentation at the CCKS2018 evaluation session and poster session, which are included within these proceedings. Finally, we would like to thank all the authors of submitted papers and the Program Committee members for their commitment.