Peer-reviewed research
Restoring Hebrew Diacritics Without a Dictionary
Elazar Gershuni and Yuval Pinter, Findings of the Association for Computational Linguistics: NAACL 2022, 2022
Read the originalRead on October 17, 2026
- What it is
- A 2022 paper from the Technion and Ben-Gurion University on restoring the vowel marks (dots) of Hebrew text. Its introduction explains that most modern Hebrew text is written without those marks.
- How much weight it carries
- Peer-reviewed in the ACL Findings series. The paper's focus is diacritic restoration, so its statements about how Hebrew is written are background, not a survey of dictation apps.
Facts taken from this source
- The 2022 NAACL paper says that because most vowels in Hebrew are encoded as diacritics, the pronunciation of words is left underspecified.
“Since most vowels are encoded via diacritics, the pronunciation of words in the text is left underspecified” (Introduction)