Deep Search parses large collections of PDF documents, such as scientific publications and patents. It detects and delimits document objects that have content, such as paragraphs and tables. This content is then extracted from the objects, such as text from paragraphs and cells from tables.
After parsing a document for its content, Deep Search interprets and enriches it.
Paragraphs of text are passed through natural language models.
These models identify language structures such as sentences and terms,
which are then classified into entity types such as a
country or a
physical property of a
Likewise, image objects are detected and interpreted by computer vision models.
Besides indexing your personal document collections, Deep Search already indexes millions of documents from public sources, such as arXiv, Pubmed, and patent offices. These documents are updated regulary and include records from curated databases.
For each material type that is mentioned in my collection of scientific papers, which of its physical properties have been tested and under which conditions?
For each company that is mentioned in my collection of annual reports, what was its total revenue per year?
Contact us if you are considering a broader use of Deep Search. We can give you access to an unlimited Deep Search service, depending on your use case. You will be able to use this service to evaluate Deep Search for larger document collections.