--- title: "Elron Bandel — papers and cards" description: "Elron Bandel: 2 paper cards in the Research library (2021–2022), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/elron-bandel/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/elron-bandel/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Elron Bandel # Elron Bandel 2 paper cards in the Research library · 2021–2022 Elron Bandel wrote 2 of the papers Mova reads, in 2021–2022, most of them on [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/); often with [Amit Seker](https://md.research.elamur.ai/free/en/authors/amit-seker/), [Dan Bareket](https://md.research.elamur.ai/free/en/authors/dan-bareket/), [Idan Brusilovsky](https://md.research.elamur.ai/free/en/authors/idan-brusilovsky/). [OpenAlex](https://openalex.org/A5002225429) · [ORCID](https://orcid.org/0009-0001-0419-8849) · [**h-index 5**](https://openalex.org/authors/A5002225429) · [93 citations](https://openalex.org/authors/A5002225429) · [35 works](https://openalex.org/works?filter=author.id:A5002225429) — openalex-snapshot, 2026-10-14 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=Elron+Bandel) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Elron+Bandel) · [dblp](https://dblp.org/search?q=Elron+Bandel) · [ACL Anthology](https://aclanthology.org/search/?q=Elron+Bandel) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Elron+Bandel) Topics: [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) 1 ## Ideas Mova took (1) From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave. - **kept** — Turn the morpheme head into a deterministic check: a segmenter's output for a token must concatenate back to the surface string. The paper's character-with-boundary view makes this a free invariant to test on every token. *([AlephBERT: Language Model Pre-training and Evaluation from…](https://md.research.elamur.ai/free/en/papers/acl-2022-seker-alephbert-language-model-pre-training/) · consonant check on every candidate (Model::spells): 0 failures on dev, test and the two-fold cv of train; kept as a gate over cut(); commit 5c24bc409)* ## Papers 1. **[AlephBERT: Language Model Pre-training and Evaluation from Sub-Word to Sentence Level](https://md.research.elamur.ai/free/en/papers/acl-2022-seker-alephbert-language-model-pre-training/)** *(2022)* `1 idea kept` Seker et al. pre-train AlephBERT, a BERT-style model for Modern Hebrew, on about 1.9 billion words: the deduplicated Hebrew part of OSCAR, all of Hebrew Wikipedia, and Hebrew tweets, with a 52K wordpiece vocabulary. The base model trained for 10 epochs and took 8 days on eight V100 GPUs. The paper's main point is… 2. **[AlephBERT: A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With](https://md.research.elamur.ai/free/en/papers/langstream-2021-seker-alephbert-hebrew-large-pre-trained/)** *(2021)* The authors build AlephBERT, a BERT-base style language model for Modern Hebrew, pre-trained on about 1.9 billion words: deduplicated OSCAR, a large set of Hebrew tweets (72% of sentences), and Hebrew Wikipedia. ## Co-authors (6) - [Amit Seker](https://md.research.elamur.ai/free/en/authors/amit-seker/) ×2 - [Dan Bareket](https://md.research.elamur.ai/free/en/authors/dan-bareket/) ×2 - [Idan Brusilovsky](https://md.research.elamur.ai/free/en/authors/idan-brusilovsky/) ×2 - [Reut Tsarfaty](https://md.research.elamur.ai/free/en/authors/reut-tsarfaty/) ×2 - Refael Greenfeld - [Refael Shaked Greenfeld](https://md.research.elamur.ai/free/en/authors/refael-shaked-greenfeld/)