Noam Ordan

3 paper cards in Mova's library · 2022–2026

Noam Ordan wrote 3 of the papers Mova reads, in 2022–2026, most of them on Universal Dependencies, Treebanks; often with Israel, Nick Howell, Amir DN Cohen.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model (2026)
The authors adapt NVIDIA's Nemotron-3 Nano sparse mixture-of-experts model (30B parameters, about 3B active per token) to Hebrew.
The Knesset Corpus: An Annotated Corpus of Hebrew Parliamentary Proceedings (2024)
The Knesset Corpus gathers the born-digital plenary (1992–2022) and committee (1998–2022) protocols of the Israeli parliament: 32.8M sentences and 384.6M tokens, with speaker and session metadata and a database of about 1,100 members and 150 factions.
A Second Wave of UD Hebrew Treebanking and Cross-Domain Parsing (2022)
The paper adds a second Hebrew UD treebank, IAHLT WIKI: 5039 sentences and about 141K tokens from 39 Hebrew Wikipedia documents in seven topics (biography, events, finance, health, law, places, miscellaneous).