WiMarka

User Manual

  • User Manual
    • What You’ll Find Here
    • Who This Manual Is For
    • Getting Started
    • For Technical Details
    • Contents
      • Installation
        • Prerequisites
        • Installation Methods
        • Verifying Installation
        • Dependencies
        • Troubleshooting
        • Uninstallation
        • Next Steps
      • Quick Start Guide
        • Prerequisites
        • Your First Evaluation
        • Understanding the Scores
        • Common Language Codes
        • Example with Errors
        • Best Practices
        • Next Steps
      • Python Library Usage
        • Basic Usage
        • Function Parameters
        • Input File Format
        • Working with Results
        • Advanced Examples
        • Error Handling
        • Best Practices
        • Common Patterns
        • Next Steps
      • Command-Line Interface (CLI) Usage
        • Basic Command
        • Command Options
        • Getting Help
        • CLI Examples
        • Working with Output
        • Batch Processing
        • Integration Examples
        • Error Handling
        • Best Practices
        • Tips and Tricks
        • Next Steps
      • Supported Languages
        • Overview
        • Language Codes
        • Supported Language Pairs
        • Language Details
        • Language-Specific Considerations
        • Future Language Support
        • Language Resources
        • Best Practices
        • Troubleshooting
      • Understanding Output Format
        • Output Structure
        • Evaluation Metrics
        • Error Detection
        • Explanations
        • Suggested Corrections
        • Output Examples by Quality
        • Best Practices for Interpretation
        • Programmatic Access
        • Next Steps
      • Examples
        • Basic Examples
        • Advanced Examples
        • Domain-Specific Examples
        • Troubleshooting Examples
        • Next Steps
  • Installation
    • Prerequisites
      • Python Version
      • Microsoft Visual Studio (Windows Only)
    • Installation Methods
      • Method 1: Install from GitHub (Recommended)
      • Method 2: Install from Source
      • Virtual Environment (Recommended)
    • Verifying Installation
      • Test Python Import
      • Test CLI Command
    • Dependencies
      • Core Dependencies
      • Data Processing
      • Deep Learning
      • Utilities
    • Troubleshooting
      • llama-cpp-python Installation Fails
      • PyTorch Installation Issues
      • Permission Errors
      • Disk Space
    • Uninstallation
    • Next Steps
  • Quick Start Guide
    • Prerequisites
    • Your First Evaluation
      • Step 1: Prepare Your Input Files
      • Step 2: Run WiMarka
        • Option A: Using Python
        • Option B: Using CLI
      • Step 3: Understanding the Output
    • Understanding the Scores
      • Fluency Score (0-100)
      • Adequacy Score (0-100)
      • Overall Score (0-100)
    • Common Language Codes
    • Example with Errors
    • Best Practices
    • Next Steps
  • Python Library Usage
    • Basic Usage
    • Function Parameters
      • wmk_eval() Parameters
        • wmk_eval()
    • Input File Format
      • Structure
      • Example Files
    • Working with Results
      • Results Dictionary Structure
    • Advanced Examples
      • Example 1: Batch Processing Multiple File Pairs
      • Example 2: Filtering Low-Quality Translations
      • Example 3: Exporting Results to CSV
      • Example 4: Integration with Translation Pipeline
    • Error Handling
    • Best Practices
    • Common Patterns
      • Pattern 1: Quality Assurance Pipeline
      • Pattern 2: Translation Comparison
    • Next Steps
  • Command-Line Interface (CLI) Usage
    • Basic Command
    • Command Options
      • Required Options
      • Optional Options
    • Getting Help
    • CLI Examples
      • Example 1: English to Cebuano
      • Example 2: English to Ilocano
      • Example 3: English to Tagalog
      • Example 4: Relative Paths
      • Example 5: Absolute Paths
    • Working with Output
      • Console Output
      • Redirecting Output to File
      • Suppressing Progress Messages
    • Batch Processing
      • Process Multiple File Pairs (Bash)
      • Process All Files in Directory
      • Parallel Processing (GNU Parallel)
    • Integration Examples
      • Integration with Make
      • Integration with Python Scripts
    • Error Handling
      • Common Errors and Solutions
      • Exit Codes
    • Best Practices
    • Tips and Tricks
      • Quick Evaluation of Single Sentence
      • Comparing Translation Systems
    • Next Steps
  • Supported Languages
    • Overview
    • Language Codes
    • Supported Language Pairs
      • Currently Supported
        • Example Usage
      • Not Currently Supported
    • Language Details
      • English (EN)
      • Cebuano (CEB)
      • Ilocano (ILO)
      • Tagalog (TGT)
    • Language-Specific Considerations
      • Script and Encoding
      • Formality and Register
      • Regional Variations
      • Code-Switching and Borrowings
      • Spelling Conventions
    • Future Language Support
      • Potential Future Additions
      • Reverse Translation Support
      • Inter-Philippine Translation
    • Language Resources
    • Best Practices
      • Choosing the Right Language Code
      • Handling Multilingual Content
      • Quality of Input Texts
    • Troubleshooting
      • Language Detection Issues
      • Low Scores Despite Good Translation
  • Understanding Output Format
    • Output Structure
      • Example Output
    • Evaluation Metrics
      • Fluency Score
      • Adequacy Score
      • Overall Score
    • Error Detection
      • Error Types
      • Error Format
      • Understanding Errors
    • Explanations
      • Natural Language Explanations
      • Contextual Information
    • Suggested Corrections
      • How Corrections Work
      • When to Use Corrections
    • Output Examples by Quality
      • Excellent Translation (90-100)
      • Good Translation (75-89)
      • Fair Translation (60-74)
      • Poor Translation (Below 60)
    • Best Practices for Interpretation
    • Programmatic Access
      • Accessing Results in Python
      • Exporting for Analysis
    • Next Steps
  • Examples
    • Basic Examples
      • Example 1: Simple English to Cebuano
      • Example 2: English to Ilocano
      • Example 3: English to Tagalog
    • Advanced Examples
      • Example 4: Quality Assurance Pipeline
      • Example 5: Comparing Multiple Translation Systems
      • Example 6: Translation Memory Integration
      • Example 7: Batch Processing with Reports
    • Domain-Specific Examples
      • Example 8: News Article Translation
      • Example 9: Educational Content
      • Example 10: Conversational Dialogues
    • Troubleshooting Examples
      • Example 11: Handling Mixed Languages
      • Example 12: Resolving Line Misalignment
    • Next Steps

Technical Manual

  • Technical Manual
    • What You’ll Find Here
    • Who This Manual Is For
    • Prerequisites
    • Documentation Structure
      • System Overview
      • API Documentation
      • Development & Extension
    • Getting Started with Development
    • Key Concepts
      • Evaluation Pipeline
      • Language Models
      • Design Principles
    • Architecture Diagram
    • Module Organization
    • Contents
      • Architecture
        • System Overview
        • High-Level Architecture
        • Core Components
        • Evaluation Pipeline
        • Data Flow
        • Model Management
        • Performance Considerations
        • Error Handling
        • Logging
        • Configuration Management
        • Extensibility Points
        • Design Patterns
        • Future Architecture Improvements
        • References
        • Next Steps
      • API Reference
        • Main Module (wimarka.main)
        • CLI Module (wimarka.cli)
        • Task Modules
        • Utility Modules
        • Type Hints
        • Constants
        • Configuration
        • Best Practices
        • See Also
      • Task Modules
        • Overview
        • error_detection Module
        • scoring Module
        • explanation Module
        • correction Module
        • Task Module Integration
        • Customization
        • Performance Considerations
        • Best Practices
        • See Also
      • Utility Modules
        • Overview
        • helper Module
        • logger Module
        • model Module
        • cache Module
        • torch Module
        • See Also
      • Language Models
        • Overview
        • Model Architecture
        • Model Management
        • Performance
        • Future Improvements
        • See Also
      • Development Guide
        • Development Setup
        • Project Structure
        • Coding Standards
        • Testing
        • Contributing
        • See Also
      • Extending WiMarka
        • Adding New Languages
        • Adding Custom Tasks
        • Custom Scoring Algorithms
        • Creating Plugins
        • Alternative Interfaces
        • Best Practices
        • See Also
    • Contributing
    • Support
  • Architecture
    • System Overview
    • High-Level Architecture
    • Core Components
      • Main Module (main.py)
      • CLI Module (cli.py)
      • Task Modules
      • Utility Modules
    • Evaluation Pipeline
      • Stage 1: Error Detection
      • Stage 2: Scoring
      • Stage 3: Explanation Generation
      • Stage 4: Correction Suggestion
    • Data Flow
    • Model Management
      • Model Loading Strategy
      • Model Types
      • Device Management
    • Performance Considerations
      • Optimization Strategies
      • Bottlenecks
      • Scalability
    • Error Handling
      • Error Handling Strategy
      • Exception Hierarchy
    • Logging
      • Logging Architecture
    • Configuration Management
      • Configuration Strategy
    • Extensibility Points
    • Design Patterns
      • Patterns Used in WiMarka
      • Trade-offs
    • Future Architecture Improvements
      • Planned Enhancements
    • References
    • Next Steps
  • API Reference
    • Main Module (wimarka.main)
      • wmk_eval()
      • wmk_eval
        • wmk_eval()
      • results Dictionary
    • CLI Module (wimarka.cli)
      • main
    • Task Modules
      • error_detection Module
        • split_words()
        • tokenize_with_spans()
        • format_tagged_sentence_using_spans()
        • error_detection()
      • scoring Module
        • classify()
        • scoring()
      • explanation Module
        • generate_explanation()
      • correction Module
        • generate_correction()
    • Utility Modules
      • helper Module
        • add_tag()
        • check_tag()
        • get_column()
        • printEvaluationResults()
      • logger Module
        • setup_logger()
      • model Module
        • load_model()
      • cache Module
      • torch Module
        • get_device()
        • move_model_to_device()
    • Type Hints
    • Constants
      • Language Codes
      • Score Ranges
    • Configuration
      • Model Identifiers
    • Best Practices
      • Using the API
      • Extending the API
    • See Also
  • Task Modules
    • Overview
    • error_detection Module
      • Purpose
      • Implementation
      • Function Signature
      • Algorithm
      • Example Usage
    • scoring Module
      • Purpose
      • Implementation
      • Function Signature
      • Scoring Methodology
      • Algorithm
      • Example Usage
    • explanation Module
      • Purpose
      • Implementation
      • Function Signature
      • Explanation Components
      • Algorithm
      • Example Usage
    • correction Module
      • Purpose
      • Implementation
      • Function Signature
      • Correction Strategy
      • Algorithm
      • Example Usage
    • Task Module Integration
      • Complete Pipeline Example
      • Data Flow Between Modules
    • Customization
      • Replacing a Task Module
      • Adding a New Task
    • Performance Considerations
      • Optimization Opportunities
    • Best Practices
      • For Task Module Development
    • See Also
  • Utility Modules
    • Overview
    • helper Module
      • Functions
        • check_tag
        • add_tag
        • printEvaluationResults
    • logger Module
      • setup_logger
    • model Module
    • cache Module
    • torch Module
    • See Also
  • Language Models
    • Overview
    • Model Architecture
      • LLM Backend
      • Model Selection
    • Model Management
      • Download and Caching
      • Model Loading
    • Performance
      • Inference Speed
      • Memory Usage
    • Future Improvements
    • See Also
  • Development Guide
    • Development Setup
      • Prerequisites
      • Clone Repository
      • Create Virtual Environment
      • Install in Development Mode
    • Project Structure
    • Coding Standards
      • Style Guide
      • Type Hints
      • Docstrings
    • Testing
      • Running Tests
      • Writing Tests
    • Contributing
      • Workflow
      • Pull Request Guidelines
      • Git Commit Messages
    • See Also
  • Extending WiMarka
    • Adding New Languages
      • Step 1: Update Language Codes
      • Step 2: Update Helper Functions
      • Step 3: Add Language-Specific Models
      • Step 4: Test
    • Adding Custom Tasks
      • Step 1: Create Task Module
      • Step 2: Integrate into Pipeline
      • Step 3: Update Results Structure
    • Custom Scoring Algorithms
    • Creating Plugins
    • Alternative Interfaces
      • Web API Example
      • GUI Example
    • Best Practices
    • See Also
WiMarka
  • Overview: module code

All modules for which code is available

  • wimarka.main
  • wimarka.tasks.correction
  • wimarka.tasks.error_detection
  • wimarka.tasks.explanation
  • wimarka.tasks.scoring
  • wimarka.utils.helper
  • wimarka.utils.logger
  • wimarka.utils.model
  • wimarka.utils.torch

© Copyright 2025, University of the Immaculate Conception - College of Computer Studies.

Built with Sphinx using a theme provided by Read the Docs.