Help Center
Topic: Recognition
What is Intelligent Word Recognition (IWR)?
Help Center Recognition • Last updated: 12 August, 2025Intelligent Word Recognition helps improve handwriting recognition accuracy by matching written responses against your predefined dictionary of expected answers. This is especially useful for questions with predictable responses like city names, course titles, or product names.
How IWR improves accuracy
Unlike standard character-by-character recognition, IWR matches entire words against your dictionary. For example:
- Standard recognition might read "New Yrok" (character error)
- IWR matches it to "New York" from your dictionary
- The correct answer is automatically verified
When to use IWR
IWR works best for questions with:
- Limited possible answers - Countries, states, cities
- Repeated responses - Course names, department names
- Common misspellings - Technical terms, brand names
- Standardized formats - ID numbers, codes
Setting up IWR
Step 1: Navigate to Dictionary settings
- Go to Surveys in your dashboard
- Select your survey
- Click the Verify tab
- Select Dictionary
Step 2: Add verification rules
- Click Add Custom Rule
- Select the question (works with Short Text and Number questions)
- Choose your matching method:
- Text is similar to - Recommended for handwritten text
- Text is equal to - Best for numbers or codes
Step 3: Enter expected values
Add your dictionary entries, one per line:
Example entries:
New York
Los Angeles
Chicago
Houston
Phoenix
Click Add to save your rule.
Best practices
For text responses
- Use "Text is similar to" for flexibility
- Include common variations (NY, New York, NYC)
- Add common misspellings you've observed
- Keep lists manageable (under 100 entries)
For numeric responses
- Use "Text is equal to" for exact matching
- Include formats with/without separators
- Add leading zeros if applicable
- Consider ranges for validation
Dictionary management tips
- Start with a small dictionary and expand based on actual responses
- Review unmatched responses regularly
- Export verified responses to identify new dictionary entries
- Group similar rules by question type
How IWR works with handwriting recognition
PaperSurvey uses advanced Handwriting Text Recognition (HTR) powered by neural networks. IWR enhances this by:
- Processing the handwritten text through HTR first
- Comparing results against your dictionary
- Auto-correcting close matches
- Flagging uncertain matches for review
Common use cases
Location questions
United States
United Kingdom
Canada
Australia
Germany
Course evaluations
Introduction to Psychology
Calculus I
Organic Chemistry
World History
English Literature
Product feedback
Model A-100
Model A-200
Model B-100
Premium Version
Standard Version
Monitoring and improvement
Review verification results
- Check the Verify tab regularly
- Look for patterns in unmatched responses
- Add frequently occurring responses to your dictionary
Optimize your rules
- Remove rarely used entries
- Combine similar variations
- Adjust matching methods based on accuracy
Troubleshooting
Issue: Too many false matches Solution: Switch from "similar to" to "equal to" for stricter matching
Issue: Valid responses not matching Solution: Add more variations to your dictionary
Issue: Numbers not matching correctly Solution: Ensure format consistency in your dictionary
IWR significantly reduces manual verification time while maintaining data accuracy. Start with common responses and refine your dictionary as you collect more data.
Topics
Get Started with PaperSurvey.io Software
Start your 14-day free trial now, no credit card required.