Roee Aharoni
Roee Aharoni wrote 2 of the papers Mova reads, in 2020–2023, most of them on Machine translation; often with Genady Beryozkin, Hila Noga, Idan Szpektor.
OpenAlex · h-index 23 · 1918 citations · 69 works — openalex, 2026-10-18
Topics: Machine translation 1
Papers
- Multilingual Sequence-to-Sequence Models for Hebrew NLP (2023)
The authors argue that Hebrew encoder-only models (AlephBERT, AlephBERT-Gimmel, HeBERT) cannot emit morphemes or labels that are not in the input, so they need extra segment-then-tag components. - KoBE: Knowledge-Based Machine Translation Evaluation (2020)
KoBE is a reference-free metric. Each source sentence and each candidate translation is linked to a large multilingual knowledge base, using entity linking. The score is the recall of source entities that are linked to the same knowledge-base entry in the candidate, clipped by the number of times each entity occurs…
Co-authors (8)
- Genady Beryozkin
- Hila Noga
- Idan Szpektor
- Markus Freitag
- Matan Eyal
- Reut Tsarfaty
- Wolfgang Macherey
- Zorik Gekhman
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/roee-aharoni/