Europeana: mapping postcards: Difference between revisions

From FDHwiki
Jump to navigation Jump to search
Line 7: Line 7:
| align="center" |Week 4
| align="center" |Week 4
|
|
*  
* Explore postcard search results on Europeana's website
*  
* Get Europeana API
*  
* Extract data from postcards using the Europeana API
| align="center" |✅
| align="center" |✅
|-
|-
Line 15: Line 15:
| align="center" |Week 5
| align="center" |Week 5
|
|
*  
* Clean data using metadata.
*  
* Analyze the data of Europeana postcards
*  
* Prepare sample image sets and explore prediction methods
| align="center" |✅
| align="center" |✅
|-
|-
Line 23: Line 23:
| align="center" |Week 6
| align="center" |Week 6
|
|
*  
* Decide to focus on postcards with text
*  
* Test and evaluate the effectiveness of multiple OCR models
*
| align="center" |✅
| align="center" |✅
|-
|-
Line 31: Line 30:
| align="center" |Week 7
| align="center" |Week 7
|
|
*  
* Use OCR and NER for prediction
*  
* Test and evaluate the effectiveness of multiple NER tools
*  
* Explore alternative forecasting methods
| align="center" |✅
| align="center" |✅
|-
|-
Line 39: Line 38:
| align="center" |Week 8
| align="center" |Week 8
|
|
*  
* Introduce ChatGPT for the prediction(OCR+GPT-3.5+NER)
*  
* Try to make predictions directly using GPT-4
*
| align="center" |✅  
| align="center" |✅  
|-
|-
Line 47: Line 45:
| align="center" |Week 9
| align="center" |Week 9
|
|
*  
* Optimize GPT-3.5 prompt for better results
*  
* Compare the results of OCR + GPT-3.5 (optimized prompts) to those of GPT-4.
*
 
| align="center" |✅  
| align="center" |✅  
|-
|-
Line 55: Line 53:
| align="center" |Week 10
| align="center" |Week 10
|
|
*  
* Complete the pipeline for the entire prediction process
*  
* Prepare a sample set to evaluate the effect
*
| align="center" |✅  
| align="center" |✅  
|-
|-

Revision as of 14:27, 6 December 2023

Project Timeline

Timeframe Task Completion
Week 4
  • Explore postcard search results on Europeana's website
  • Get Europeana API
  • Extract data from postcards using the Europeana API
Week 5
  • Clean data using metadata.
  • Analyze the data of Europeana postcards
  • Prepare sample image sets and explore prediction methods
Week 6
  • Decide to focus on postcards with text
  • Test and evaluate the effectiveness of multiple OCR models
Week 7
  • Use OCR and NER for prediction
  • Test and evaluate the effectiveness of multiple NER tools
  • Explore alternative forecasting methods
Week 8
  • Introduce ChatGPT for the prediction(OCR+GPT-3.5+NER)
  • Try to make predictions directly using GPT-4
Week 9
  • Optimize GPT-3.5 prompt for better results
  • Compare the results of OCR + GPT-3.5 (optimized prompts) to those of GPT-4.
Week 10
  • Complete the pipeline for the entire prediction process
  • Prepare a sample set to evaluate the effect
Week 11
  • Explore the visualization methods
  • Refine the test set and analyze it
Week 12
  • Use the TA's annotation tool for test set evaluation
  • Build the visualization platform
Week 13
  • Testing and refinement of the Web application
Week 14
  • Final report preparation and presentation