{"id":9,"date":"2021-10-14T18:57:12","date_gmt":"2021-10-14T18:57:12","guid":{"rendered":"https:\/\/www.isi.edu\/centers-ckg\/?page_id=9"},"modified":"2022-04-19T21:06:11","modified_gmt":"2022-04-19T21:06:11","slug":"about","status":"publish","type":"page","link":"https:\/\/www.isi.edu\/centers-ckg\/","title":{"rendered":"About CKG"},"content":{"rendered":"\n\n\t\t\t\t\"Center\n
\n

Solving the world’s problems using knowledge<\/h2>\n<\/section>\n\t

The Center on Knowledge Graphs research group creates new approaches for amplifying artificial intelligence using structured knowledge. The group combines expertise from artificial intelligence, machine learning, the Semantic Web, natural language processing, databases, information retrieval, geospatial analysis, business, social sciences, and data science. The center is composed of 16 senior ISI researchers, guiding the work of 17 PhD students, 12 MS students, and six researcher programmers.<\/p>\n

Our group has built tools and knowledge graphs to address challenging, real-world problems such as enabling common sense reasoning, reducing global food insecurity, fighting human trafficking, assessing medical and clinical data, fostering pharmacological discovery, ensuring scientific reproducibility, understanding supply chains, analyzing competition in business, integrating cultural heritage data, creating more engaging dialogue agents, and identifying social and moral norms in cultures. Supporting this vast array of projects are state-of-the-art tools for entity resolution and entity linking, automated semantic modeling, probabilistic reasoning, text generation, knowledge retrieval, table understanding, knowledge curation, error detection, event extraction, and visualization and exploration of knowledge.<\/p>\n

\n

Research Highlights<\/h2>\n<\/section>\n\t
  1. <\/li>
  2. <\/li>
  3. <\/li>
  4. <\/li>
  5. <\/li>
  6. <\/li>
  7. <\/li><\/ol>
    \"Table\"
    Representing Numbers in NLP: a Survey and a Vision<\/div><\/div><\/a><\/div>
    \"Graphic\"
    Numeracy enhances the Literacy of Language Models<\/div><\/div><\/a><\/div>
    \"Graphic\"
    RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms<\/div><\/div><\/a><\/div>
    \"Graphic\"
    Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation<\/div><\/div><\/a><\/div>
    \"Graphic\"
    A Hybrid Probabilistic Approach for Table Understanding<\/div><\/div><\/a><\/div>
    \"Graphic\"
    Tabular Functional Block Detection with Embedding-based Agglomerative Cell Clustering<\/div><\/div><\/a><\/div>
    \"Graphic\"
    Contextualized Scene Imagination for Generative Commonsense Reasoning<\/div><\/div><\/a><\/div><\/div>