conceptology

Goals:

• Better interpretation and visualization of the concept lists and the individual concepts.
• More semantic user-interaction with the text data, eg.: understand natural language user queries better and formulate synthesized answers.

Notes:

• concept inception –> form –> concept extraction
• idea-class versus form-instance
• simple user-language for creating concept queries

• semantic sentence embedding encoding-decoding:
  • demo: semantic book search
    • universal sentence encoder
  • video: “Representations for Language: From Word Embeddings to Sentence Meanings”
• NLP meaning visualizations:
  • embeddings (“mapping from discrete objects, such as words, to vectors of real numbers”):
    • video: visualizing high-dimensional spaces
    • tensorflow embeddings projector (code)
• models:
  • “A Conceptual Space Logic” (pdf)
  • Metamath.org (tiny language that can express theorems in abstract mathematics)
• related keywords: conceptology, concept logic, concept heuristic, ontology, semiotics, Curry–Howard correspondence, semantic web, automated text classification