Project information

Inteligentní software pro sémantické hledání dokumentů (ISSHD)

Investor logo
Project Identification
TD03000295
Project Period
1/2016 - 12/2017
Investor / Pogramme / Project type
Technology Agency of the Czech Republic
MU Faculty or unit
Faculty of Informatics
Project Website
https://scaletext.com
Keywords
scalable semantic search systems; semantic search; document topic modeling; machine learning; search; deep learning
Cooperating Organization
RaRe Technologies s.r.o.

Our society, research and culture is defined by words, which in today's information society
constitute _documents_.
Project goal is to develop a database system (software),
which will allow searching based on related documents based on their _meaning_ (semantics).
System Scaletext consists from three parts:

  • semantic analysis: arbitrary unstructured document in natural language (English, Czech) is analyzed
  • indexing: document topics and structure are represented and stored internally using _semantic_


representation in such a way, that system is then capable of semantic similarity search given a document query.

  • search: given input query document, system finds semanticaly closed documents, that are closest to [latent] meaning of the query, even though they do not share same keywords

Results

https://www.rvvi.cz/cep?s=jednoduche-vyhledavani&ss=detail&n=0&h=TD03000295

Publications

Total number of publications: 9