[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/hbo-2024-rosenthal-d-nikud-enhancing-hebrew-diacritization/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Ancient Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/hbo/) / D-Nikud: Enhancing Hebrew Diacritization with LSTM and Pretrained Models

# D-Nikud: Enhancing Hebrew Diacritization with LSTM and Pretrained Models

**Authors:** Adi Rosenthal, Nadav Shaked · **Year:** 2024 · **Venue:** arXiv 2402.00075 (student project, Reichman University) **Link:** [arxiv.org/abs/2402.00075](https://arxiv.org/abs/2402.00075) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)

[**0** citations](https://openalex.org/works?filter=cites:W4391505274) openalex · 2026-10-18[**1** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/hbo-2024-rosenthal-d-nikud-enhancing-hebrew-diacritization/) of the 140673 papers whose bibliographies we read[arXiv:2402.00075](https://openalex.org/S4306400194)[licence](http://creativecommons.org/licenses/by/4.0/)

- [Publisher's page](https://arxiv.org/abs/2402.00075)
- [PDF](https://arxiv.org/pdf/2402.00075)
- [arXiv 2402.00075](https://arxiv.org/abs/2402.00075)
- [OpenAlex](https://openalex.org/W4391505274)

**Authors (2)**

1. [Adi Rosenthal](https://openalex.org/A5036223027) h 2 · 290 citations · 10 works
2. [Nadav Shaked](https://openalex.org/A5108144964) [ORCID](https://orcid.org/0009-0002-5615-9478) · h 0 · 0 citations · 3 works

Citations and author metrics from openalex (2026-10-18); authors with the same name are not always told apart.

## What it is about

Another Hebrew vocaliser: frozen TavBERT character embeddings, two Bi-LSTM layers and three classifier heads per letter (vowel, dagesh, shin/sin dot). Training data are Nakdimon's corpora (about 1.8 million pre-modern tokens: Ben-Yehuda, Mishneh Torah from Mamre, short stories; and 1.5 million modern tokens auto-pointed by Dicta and corrected) plus Dicta's material, all in full spelling (ktiv male). On Nakdimon's test set it leads on decision and character accuracy (about 98.3 / 97) but trails Dicta on whole-word accuracy; it is best on texts addressed to women, where the gender of second-person forms hides in the vowels. By genre, law and modern prose score highest (CHA ≈ 97–99), while biblical text is worst by far (CHA 90.7, word accuracy 75.7).

## Ideas

- I1. The biblical score (three words in four right) shows that modern vocalisers do not transfer to Biblical Hebrew; quote it in the comparison chapter as one more measured reason why Modern Hebrew tools misread the Bible.
- I2. Mova's fully pointed Torah is itself a gold test for any vocaliser: strip the points (keep consonants and the matres as written), run the tool, score by the paper's DEC/CHA/WOR/VOC. A cheap measure for a neural teacher, never a part of Mova's answers.
- I3. Second-person gender lives in the vowels (ךָ vs ךְ, אַתָּה/אַתְּ, qatal תָּ/תְּ). Check that every second-person form in the trees carries `Gender` and that it agrees with the addressee in `prag`; a disagreement is a converter or data defect.

## For Mova

I1 is a sentence in [12. Biblical, Mishnaic and Modern Hebrew compared](https://md.mova.elamur.ai/free/en/docs/languages/hbo/12-biblical-mishnaic-modern/). I2 is a measure described in `13-mova-tools.md`, run only with the operator's word if a model must be installed. I3 is a FEATS check in `tools/macula` and an agreement test between the trees and `tools/macula/src/prag.rs` (addressee), with the rule in `05-pronouns-particles.md`.

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [arXiv 2402.00075](https://arxiv.org/abs/2402.00075)

```
@misc{rosenthal2024d,
  title = {{D-Nikud: Enhancing Hebrew Diacritization with LSTM and Pretrained Models}},
  author = {Rosenthal, Adi and Shaked, Nadav},
  year = {2024},
  eprint = {2402.00075},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.00075}
}
```

- [← previous Some Notes on Lexicographic Criticism and Biblical Hebrew Studies. Revisiting David J. A. Clines's Method](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2024-ortiz-some-notes-lexicographic-criticism-biblical/)
- [next → Large Language Models and Biblical Hebrew: Limitations, pitfalls, opportunities](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2024-staps-large-language-models-biblical-hebrew/)
- [↑ back to Ancient Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/hbo/)

## References

3 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Elazar Gershuni and Yuval Pinter, Restoring Hebrew Diacritics Without a Dictionary, 2022, March, https:// arxiv.org/pdf/2105.05209.pdf. [5] Sepp Hochreiter and Jurgen Schmidhuber, LONG SHORT-TERM MEMORY, 1997, April, https://www.bioinf.jku.at/publications/older/2604.pdf, MIT Press. [↗](https://arxiv.org/abs/2105.05209) [our card](https://md.mova.elamur.ai/free/en/docs/papers/findings-2022-gershuni-restoring-hebrew-diacritics-without-dictionary/)
2. Avi Shmidman and Shaltiel Shmidman and Moshe Koppel and Yoav Goldberg, Nakdan: Professional Hebrew Diacritizer, 2020, March, [https://arxiv.org/pdf/2005.03312.pdf](https://arxiv.org/pdf/2005.03312.pdf). [6] Stav Klein and Reut Tsarfaty, Getting the life out of living: How Adequate Are Word-Pieces for Modelling Complex Morphology?, 2020, July, https://aclanthology.org/2020. sigmorphon-1.24. [↗](https://arxiv.org/pdf/2005.03312.pdf) [our card](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2020-shmidman-nakdan-professional-hebrew-diacritizer/)
3. Omri Keren and Tal Avinari and Reut Tsarfaty and Omer Levy, Breaking Character: Are Subwords Good Enough for MRLs After All?, 2022, April, https://arxiv.org/pdf/2204.04748.pdf. [↗](https://arxiv.org/abs/2204.04748)