1 of 8

Mitteilungsblatt

progress so far

2 of 8

NER experiments (Benjamin)

3 of 8

Manual markup production (Miriam, Ursula, Harold, Henny)

4 of 8

Manual markup production (Miriam, Ursula, Harold, Henny)

5 of 8

NER evaluation against the markup (Daniil)

6 of 8

OCR and refining of the list of names mentioned in birthday wishes and obituaries (Harold, Henny, Ursula)

7 of 8

OCR and refining of the list of names mentioned in birthday wishes and obituaries (Harold, Henny, Ursula)

​

8 of 8

What’s next?

  • keep refinining lists
  • integrating the digitized persons list into the NER pipeline
  • modeling the person attributes
  • integrating our data with other datasets (with help of Yael)
  • the שפה עברית part