Short answer:
Focus on including important terms, relevant synonyms, and common variations used in your documents, organized into logical Categories. Always include one catch-all Category for general terms, and review and update regularly to keep your Semantic Map aligned with your Project content.
Full explanation:
A well-built Semantic Map helps AskTuring understand the language used in your documents and recognize how related concepts connect. Categories organize your terms into meaningful groups, making the map easier to manage and improving the accuracy of the AI’s responses.
Behind the scenes, this process is powered by AskTuring’s patented technology, which links terms, Categories, and alternatives together so the AI can interpret and respond to user queries more intelligently.
1. Create Categories
Most Semantic Maps work best with 4–10 Categories.
Each Category should group related terms that make sense together—such as Departments, Processes, Regulations, or Client Names.
Always include one catch-all Category, typically called General Terms, for words and phrases that don’t fit neatly elsewhere.
2. Identify key terms from your documents
Review your Project content to find specialized terms, acronyms, product names, and industry jargon that are important for accurate search results.
3. Add synonyms and alternative phrases
For each key term, include variations that users might type differently when asking a question. Examples include:
Synonyms (e.g., attorney and lawyer)
Acronyms and full names (e.g., IRS and Internal Revenue Service)
Common misspellings or abbreviations (if they appear frequently in your documents)
4. Group terms under the right Category
Assign each term to the Category where it logically belongs.
Use the General Terms Category only for items that clearly don’t fit in any other group.
5. Keep it focused
Avoid adding unrelated or rarely used words. Too many loosely related terms can reduce search precision and confuse the AI.
6. Update regularly
Each time you upload new documents or add new subject areas to a Project, review and update your Semantic Map to capture any new terminology, acronyms, or key phrases that appear.
Why It Matters
A well-maintained Semantic Map, supported by AskTuring’s patented language-linking technology, improves both:
Recall: Finding all the relevant documents that match a query.
Precision: Reducing irrelevant or off-topic results.
By structuring your terms into clear Categories (with one catch-all for General Terms), you ensure that AskTuring can handle both detailed and broad queries with greater accuracy.
Tips
Involve subject matter experts when building your Semantic Map to ensure accurate terminology.
Review your search logs to identify terms that users are searching for but not finding easily.
Schedule a quarterly review to clean up or expand your Semantic Map.
Keep Category names simple and intuitive so they’re easy to navigate and maintain.
Use consistent capitalization and formatting across all terms for best results.