The Nathan API for Language / Text and Data
Topic-Mapper™ is a specialized solution for language processing: language in form of text or data (i.e. values). Topic-Mapper™ imports the data directly into the holosemantic data space. So the data directly stimulates the holosemantic ai-one™ net.
With the ai-one™ Topic-Mapper, developers can build intelligent text applications that deliver sense-making and learning capabilities for semantic discovery, knowledge collaboration, sentiment analysis, and classification. AI and learning are inherent to the technology and the API gives developers commands they need to “build a learning machine” with the attributes critical to their application
- provides semantic analysis and matching for text
- straightforward and flexible API for inherent semantic associative search and phonetic analysis
- human language independent
- requires only basic structuring of input text
- ongoing “teaching” via user defined contexts
Cloud hosted API for Development, Prototyping & Testing
Topic-Mapper is ideal for internal IT teams to build machine learning applications to mine unstructured data. It is a “must have” tool for any IT department that wants to quickly and easily build intelligent applications. The system takes less than a day to learn.
Common use cases for building custom applications using Topic-Mapper include:
- Knowledge management systems using semantic search and retrieval. For example, finding related patent filings or PubMed articles.
- Mining unstructured text documents to find similar concepts or ideas. ai-BrainDocs is an eDiscovery application and new business built on Topic-Mapper. It enables legal departments to scan documents for different ideas that use the same words — something that can’t be done using other search, semantic or statistical approaches such as keyword searches, LSI, LSA, LDA, etc.
- Auto-tagging and classifying text (either documents or social media feeds).
- Comparing the content of multiple information sources.