Named entity recognition

10 paper cards from Mova's library

What it is

Named entity recognition, NER for short, finds the names in a text and says what kind of thing each one names: a person, a place, an organization, a date, an amount. In «Abraham went down to Egypt», a NER system marks «Abraham» as a person and «Egypt» as a place.

It is harder than it looks. A name can be several words long, the same name can be a person or a company or a town, capital letters help in English but not in Hebrew, and new names appear every day. Systems learn from texts where people have marked the names, and they are measured by how many names they find and type exactly right.

How Mova does it

Mova has no separate NER tagger. Its tagger marks proper nouns in the dependency tree, the coreference sieve gives every mention a semantic class (person, place, organization, time and others) and uses it to decide what «it» or «she» can refer to, and the frames reader records who acts in every clause. The classes come with the reason they were chosen.

• coref — the mentions and their classes
• en — the tagger and parser
• Frames: who did what to whom

The papers (10)

Cards with a measured or kept idea first, then by citations.

1. AlephBERT: A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With — Amit Seker, Elron Bandel, Dan Bareket, Idan Brusilovsky et al., 2021 · 23 citations
2. Neural Modeling for Named Entities and Morphology (NEMO2) — Dan Bareket, Reut Tsarfaty, 2021 · 18 citations
3. Unsupervised AMR-Dependency Parse Alignment — Wei-Te Chen, Martha Palmer, 2017 · 13 citations
4. English Multiword Expression-aware Dependency Parsing Including Named Entities — Akihiko Kato, Hiroyuki Shindo, Yuji Matsumoto, 2017 · 4 citations
5. Domain-Aware Error Correction for Citation NER in Medieval Hebrew Responsa — Shmuel LIebeskind, Maayan Zhitomirsky-Geffet, Binyamin Katzoff, Nati Ben-Gigi et al., 2026
6. Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya — Hailay Kidu Teklehaymanot, Debela Desalegn Yadeta, Wolfgang Nejdl, 2026
7. Towards Named-Entity and Coreference Annotation of the Hebrew Bible — Daniel G. Swanson, Bryce D. Bussert, Francis Tyers, 2024
8. Explicit Morphological Knowledge Improves Pre-training of Language Models for Hebrew — Eylon Gueta, Omer Goldman, Reut Tsarfaty, 2023
9. BTPK-based interpretable method for NER tasks based on Talmudic Public Announcement Logic — Yulin Chen; Beishui Liao; Bruno Bentzen; Bo Yuan; Zelai Yao; Haixiao Chi;, Dov Gabbay, 2022
10. A Survey of Qualitative Error Analysis for Neural Machine Translation Systems — Denise Díaz, James Cross, Vishrav Chaudhary, Ahmed Kishky et al., 2020

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/topics/named-entity-recognition/