How to Use Excel and Copilot to Identify Language Families
Question details
The user needs to classify a list of languages by their respective language family and subfamily using Excel formulas, Power Query, or Copilot Pro.

- Product
- Microsoft Excel, Copilot Pro
- Device & OS
- not provided
- Scenario
- Organizing and classifying a dataset containing various languages into proper linguistic families and subfamilies.
- Observed behavior
- The user wants to automate repetitive classification tasks using accurate formulas or AI prompts.
Ensure you have a reliable reference table or dataset mapping languages to their families, as AI-generated linguistic data can sometimes be disputed or incomplete.
Use XLOOKUP with a Reference Table
The most accurate and repetitive way to classify languages is to build a definitive reference table and use the XLOOKUP function.
Relying solely on AI for specialized classifications can lead to inaccuracies. Setting up a static reference table guarantees precise and standardized categorization across your entire dataset.
Create a new sheet named 'Reference' with three columns: Language, Language Family, and Subfamily, and populate it with verified linguistic data.
In your main data table, select the empty cell in the 'Language Family' column next to your first target language.
Enter the formula =XLOOKUP(A2, Reference!A:A, Reference!B:C) to fetch both the family and subfamily simultaneously.
Press Enter, then drag the fill handle down to apply this formula to your entire dataset.

Prompt Copilot Pro to Classify Languages
Use Copilot in Excel to automatically generate a draft mapping of language families without writing manual formulas.
Use WPS Spreadsheet to Organize Language Data
WPS Spreadsheet offers powerful lookup functions like XLOOKUP and integrates WPS AI to help you manage complex datasets and generate classification formulas effortlessly.
- 1. Open your dataset: Launch WPS Spreadsheet and open the document containing your language data.
- 2. Prepare your reference data: Create a dedicated reference sheet containing the accurate linguistic families and subfamilies.
- 3. Utilize XLOOKUP or WPS AI: Use the built-in XLOOKUP function or ask WPS AI to generate the exact lookup formula for your table.
- 4. Populate the columns: Apply the formula across your dataset for instant, accurate classification.

Frequently Asked Questions
Can Copilot in Excel be fully trusted with linguistic classifications?
No, Copilot generates classifications based on available AI training data, which might include disputed or oversimplified linguistic groupings. It is highly recommended to manually review the results against a reliable academic reference.
Why should I use XLOOKUP instead of VLOOKUP for this task?
XLOOKUP is more flexible than VLOOKUP. It can return multiple columns at once (such as returning both Family and Subfamily simultaneously) and does not require the lookup column to be on the far left of your reference table.
Can I use Power Query to classify languages instead of formulas?
Yes, you can load your main dataset and your reference table into Power Query, then perform a 'Merge Queries' operation to join the language families to your main list automatically. This is especially useful for very large datasets.




