Knowledge has played a fundamental role since the inception of Artificial Intelligence. While the forms in which algorithms have leveraged knowledge have evolved over time, the need for efficient representations is ever more critical. Recent advances of AI, such as the stunning performance of large language models, have relied on the large amount of data available on the Web. There is growing agreement among researchers that it's important to look beyond the sheer volume of data, and instead also prioritize the development of methods that are accurate, precise, and efficient for capturing knowledge.

The International Conference on Knowledge Capture, K-CAP, aims at bringing together an interdisciplinary group of researchers on a diverse set of topics with interest in the development of knowledge capture. This involves the design and development of formalisms, methods and tools that enable efficient and precise extraction and organization of knowledge from different sources and for different modalities of use including, for example, automated reasoning, machine learning and human-machine teaming.

To enable a vibrant and constructive discussion on scalable and precise knowledge capture, K-CAP 2023, calls for the participation of researchers from diverse areas of Artificial Intelligence, including, but not limited to, knowledge representation and reasoning, knowledge acquisition, semantic web, intelligent user interfaces for knowledge acquisition and retrieval, query processing and question answering over heterogeneous knowledge bases, novel evaluation paradigms, problem-solving and reasoning, ethics and AI, explainability, neuro-symbolic AI, agents, information extraction from structured or unstructured data, machine learning and representation learning, information enrichment and visualization, as well as researchers interested in cyber-infrastructures to foster the publication, retrieval, reuse, and integration of data.

Topics of interest

Areas of interest for submissions to K-CAP 23 include, but are not limited to, the following topics:

    Knowledge representation
    Knowledge acquisition
    Ethical aspects related to knowledge capture and acquisition
    Knowledge capture for supporting explainability and, vice-versa, leveraging explainability approaches for knowledge capture
    Intelligent user interfaces for knowledge acquisition and retrieval
    Innovative query processing and question answering over heterogeneous knowledge bases
    Novel evaluation paradigms for knowledge capture
    Problem-solving and reasoning
    The role of knowledge and knowledge capture in neuro-symbolic AI
    Compact knowledge representation such as constraint networks and graphical models
    Knowledge capture in multi-agent systems
    Intersection of planning and knowledge capture
    Information extraction from text
    The role of metadata in knowledge capture processes
    Multi-modal knowledge capture from text, tables, images, video or sound
    Machine learning and representation learning
    Information enrichment and visualization
    The role of language models in knowledge graph construction and representation
    Techniques for extracting structured knowledge from large-scale language models
    Applications of deep learning to knowledge representation and reasoning, such as graph neural networks and graph convolutional networks
    Advancements in representation learning and deep learning for knowledge capture
    Utilizing deep learning for information extraction from structured and unstructured data to improve knowledge capture