[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/shaltiel-shmidman/) [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/) / [authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/) / Shaltiel Shmidman # Shaltiel Shmidman 13 paper cards in Mova's library · 2020–2026 Shaltiel Shmidman wrote 13 of the papers Mova reads, in 2020–2026, most of them on [Part-of-speech tagging](https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/), [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/); often with [Avi Shmidman](https://md.mova.elamur.ai/free/en/docs/papers/authors/avi-shmidman/), [Moshe Koppel](https://md.mova.elamur.ai/free/en/docs/papers/authors/moshe-koppel/), [Amir DN Cohen](https://md.mova.elamur.ai/free/en/docs/papers/authors/amir-dn-cohen/). [OpenAlex](https://openalex.org/A5041361841) · [**h-index 3**](https://openalex.org/authors/A5041361841) · [30 citations](https://openalex.org/authors/A5041361841) · [21 works](https://openalex.org/works?filter=author.id:A5041361841) — openalex, 2026-10-18 The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Shaltiel+Shmidman) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Shaltiel+Shmidman) · [dblp](https://dblp.org/search?q=Shaltiel+Shmidman) · [ACL Anthology](https://aclanthology.org/search/?q=Shaltiel+Shmidman) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Shaltiel+Shmidman) Topics: [Part-of-speech tagging](https://md.mova.elamur.ai/free/en/docs/papers/topics/part-of-speech-tagging/) 2 · [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/) 1 ## Ideas Mova took (1) From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave. - **measured, no gain** — Constrain prefix segmentation by a table of legal proclitic sets keyed on the word's initial letters. *([DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/arxivrecent-2023-shmidman-dictabert-state-art-bert-suite/) · legal prefix-chain table as a hard filter (chain:N, learned chains): split right dev 97.38 / 94.21 unchanged, cv +-0.01 (pointed, unpointed); the learned…)* ## Papers 1. **[Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2026-shmidman-dicta-lm-3-0-advancing/)** *(2026)* Dicta-LM 3.0 is an open-weight family of Hebrew-and-English LLMs at 24B, 12B and 1.7B parameters. Each was made by continued pre-training of an existing base model (Mistral-Small-3.1, Nemotron Nano V2, Qwen3-1.7B) on about 100B Hebrew tokens mixed with 30B English tokens, then post-trained with SFT, DPO and GRPO for… 2. **[HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2026-kayzer-hebatron-hebrew-specialized-open-weight/)** *(2026)* The authors adapt NVIDIA's Nemotron-3 Nano sparse mixture-of-experts model (30B parameters, about 3B active per token) to Hebrew. 3. **[NeoDictaBERT: Pushing the Frontier of BERT models for Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2025-shmidman-neodictabert-pushing-frontier-bert-models/)** *(2025)* The authors move the NeoBERT encoder design (pre-norm RMSNorm, RoPE, SwiGLU, 28 layers at width 768, 4,096-token context) to Hebrew. 4. **[Restoring Missing Spaces in Scraped Hebrew Social Media](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2025-shmidman-restoring-missing-spaces-scraped-hebrew/)** *(2025)* Scraped web text often runs two words together, and in unvocalised Hebrew one conflated string can usually be split in several valid ways, so a dictionary lookup does not settle it. 5. **[MRL Parsing Without Tears: The Case of Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/findings-2024-shmidman-mrl-parsing-without-tears-case/)** *(2024)* Parsers for morphologically rich languages either run a pipeline (segment, tag, parse), which passes errors forward, or a joint lattice over all segmentations, which is slow and needs a lexicon. 6. **[Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities](https://md.mova.elamur.ai/free/en/docs/papers/arxivrecent-2024-shmidman-adapting-llms-hebrew-unveiling-dictalm/)** *(2024)* The paper adapts Mistral-7B to Hebrew by continued pre-training on about 200B tokens of half Hebrew and half English. 7. **[OtoBERT: Identifying Suffixed Verbal Forms in Modern Hebrew Literature](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2024-shmidman-otobert-identifying-suffixed-verbal-forms/)** *(2024)* Modern Hebrew literature sometimes fuses a verb with its direct-object pronoun into one word. The fused form is often identical to a common verb with another meaning, so readers are misled until the sentence ends. Annotators found 222 suffixed verbs in 135K words of literature (17.76 per 10K) against 7 in 185K words… 8. **[DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/arxivrecent-2023-shmidman-dictabert-state-art-bert-suite/)** *(2023)* The paper presents DictaBERT, a BERT-architecture model for Modern Hebrew, pre-trained with masked language modelling only (next-sentence prediction removed) on about 3.8B tokens: 70% cleaned HeDC4 web text and 30% news, blogs, subtitles and novels. 9. **[Introducing DictaLM -- A Large Generative Language Model for Modern Hebrew](https://md.mova.elamur.ai/free/en/docs/papers/langstream-2023-shmidman-introducing-dictalm-large-generative-language/)** *(2023)* The authors release DictaLM, a 7B-parameter generative model for Modern Hebrew, trained on about 7.5 billion tokens. 10. **[Introducing BEREL: BERT Embeddings for Rabbinic-Encoded Language](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2022-shmidman-introducing-berel-bert-embeddings-rabbinic/)** *(2022)* A short paper releasing a BERT-base model trained on about 220 million words of Rabbinic Hebrew (the Sefaria and Dicta libraries). 11. **[Large Pre-Trained Models with Extra-Large Vocabularies: A Contrastive Analysis of Hebrew BERT Models and a New One to Outperform Them All](https://md.mova.elamur.ai/free/en/docs/papers/hbo-2022-gueta-large-pre-trained-models-extra/)** *(2022)* The authors train AlephBERTGimmel, a Modern Hebrew BERT with a 128K word-piece vocabulary (earlier models had 2.4K–52K), on the same ~2 billion words as AlephBERT. 12. **[Nakdan: Professional Hebrew Diacritizer](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2020-shmidman-nakdan-professional-hebrew-diacritizer/)** *(2020)* Nakdan adds vowel points to undiacritized Hebrew, for modern, Rabbinic and poetic texts, through a web interface that lets an editor choose among the alternatives. 13. **[A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration](https://md.mova.elamur.ai/free/en/docs/papers/findings-2020-shmidman-novel-challenge-set-hebrew-morphological/)** *(2020)* Hebrew homographs are often unbalanced: one analysis is 30 to 129 times more frequent than the other. A tagger can then score well on the majority reading and fail on the minority one, which is the reading that matters in rare cases. The authors build a challenge set of 21 homographs (12 unbalanced, 9 balanced) with… ## Co-authors (23) - [Avi Shmidman](https://md.mova.elamur.ai/free/en/docs/papers/authors/avi-shmidman/) ×12 - [Moshe Koppel](https://md.mova.elamur.ai/free/en/docs/papers/authors/moshe-koppel/) ×10 - [Amir DN Cohen](https://md.mova.elamur.ai/free/en/docs/papers/authors/amir-dn-cohen/) ×3 - [Joshua Guedalia](https://md.mova.elamur.ai/free/en/docs/papers/authors/joshua-guedalia/) ×3 - [Reut Tsarfaty](https://md.mova.elamur.ai/free/en/docs/papers/authors/reut-tsarfaty/) ×3 - [Cheyn Shmuel Shmidman](https://md.mova.elamur.ai/free/en/docs/papers/authors/cheyn-shmuel-shmidman/) ×2 - Amir David Nissan Cohen - [Amit Seker](https://md.mova.elamur.ai/free/en/docs/papers/authors/amit-seker/) - [Dan Bareket](https://md.mova.elamur.ai/free/en/docs/papers/authors/dan-bareket/) - Dan Revital - Eli Handel - [Eylon Gueta](https://md.mova.elamur.ai/free/en/docs/papers/authors/eylon-gueta/) - Kate Zinkovskaia - Noam Kayzer - [Noam Ordan](https://md.mova.elamur.ai/free/en/docs/papers/authors/noam-ordan/) - Omer Baruch - Or Levi - Ori Bar Joseph - Sarel Weinberger - Smadar Arvatz - Tal Geva - [Yoav Goldberg](https://md.mova.elamur.ai/free/en/docs/papers/authors/yoav-goldberg/) - Zevi Apini - [← previous Shai Gordin](https://md.mova.elamur.ai/free/en/docs/papers/authors/shai-gordin/) - [next → Shammur Chowdhury](https://md.mova.elamur.ai/free/en/docs/papers/authors/shammur-chowdhury/) - [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)