CONCEPT SEARCH

Just what is “Concept Search?” We are asked that question a lot, particularly as people become more frustrated with the limitations of traditional search engines. Concept Search is:

Search based on Meaning, not Spelling.

Boolean search finds documents based on specific shared character strings. If your search term doesn’t exist in a document, you never see it. Concept search returns relevant documents regardless of shared terms or even a common language. It gracefully handles degraded documents like those processed by OCR where Boolean search quickly breaks.

Organic not Artificial

Thesaurus and ontology-based searches find documents based on human-coded mappings of terms which can be subjective, narrow, and incomplete. Concept search derives meaning from documents organically through a rigorous mathematical analysis of the relationship between terms across documents. It requires no outside assistance from people or dictionaries.

Dynamic not Static

As the meaning of terms change, Concept search changes with them. Human-coded ontologies can’t keep up.

This capability is at the heart of CAAT, Content Analyst’s powerful Advanced Text Analytics platform. CAAT can automatically associate any search string – from a few words to an entire book – to all conceptually-similar documents contained in a given index. It can then provide a direct measure of the conceptual similarity of this original search string to all the other documents in that index – from most similar to most dissimilar. It accomplishes this via advanced vector geometry and mathematics, so CAAT never needs lists of synonyms, keywords, or dictionaries to find relevant documents.

All Content Analyst technology functions hinge on this conceptual analysis and comparison capability. A wide variety of experiments have demonstrated that the technology in CAAT accurately captures conceptual content and that proximity of objects or documents in that geometric “conceptual space” is a remarkably valid measure for conceptual similarity without any additional human intervention.