@inproceedings{rozhkov-loukachevitch-2026-learning,
title = "Learning Nested Named Entity Recognition from Flat Annotations",
author = "Rozhkov, Igor and
Loukachevitch, Natalia V",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.50/",
pages = "649--663",
ISBN = "979-8-89176-383-8",
abstract = "Nested named entity recognition identifies entities contained within other entities, but requires expensive multi-level annotation. While flat NER corpora exist abundantly, nested resources remain scarce. We investigate whether models can learn nested structure from flat annotations alone, evaluating four approaches: string inclusions (substring matching), entity corruption (pseudo-nested data), flat neutralization (reducing false negative signal), and a hybrid fine-tuned + LLM pipeline. On NEREL, a Russian benchmark with 29 entity types where 21{\%} of entities are nested, our best combined method achieves 26.37{\%} inner F1, closing 40{\%} of the gap to full nested supervision. Code is available at https://github.com/fulstock/Learning-from-Flat-Annotations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rozhkov-loukachevitch-2026-learning">
<titleInfo>
<title>Learning Nested Named Entity Recognition from Flat Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Rozhkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Loukachevitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>Nested named entity recognition identifies entities contained within other entities, but requires expensive multi-level annotation. While flat NER corpora exist abundantly, nested resources remain scarce. We investigate whether models can learn nested structure from flat annotations alone, evaluating four approaches: string inclusions (substring matching), entity corruption (pseudo-nested data), flat neutralization (reducing false negative signal), and a hybrid fine-tuned + LLM pipeline. On NEREL, a Russian benchmark with 29 entity types where 21% of entities are nested, our best combined method achieves 26.37% inner F1, closing 40% of the gap to full nested supervision. Code is available at https://github.com/fulstock/Learning-from-Flat-Annotations.</abstract>
<identifier type="citekey">rozhkov-loukachevitch-2026-learning</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.50/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>649</start>
<end>663</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Nested Named Entity Recognition from Flat Annotations
%A Rozhkov, Igor
%A Loukachevitch, Natalia V.
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F rozhkov-loukachevitch-2026-learning
%X Nested named entity recognition identifies entities contained within other entities, but requires expensive multi-level annotation. While flat NER corpora exist abundantly, nested resources remain scarce. We investigate whether models can learn nested structure from flat annotations alone, evaluating four approaches: string inclusions (substring matching), entity corruption (pseudo-nested data), flat neutralization (reducing false negative signal), and a hybrid fine-tuned + LLM pipeline. On NEREL, a Russian benchmark with 29 entity types where 21% of entities are nested, our best combined method achieves 26.37% inner F1, closing 40% of the gap to full nested supervision. Code is available at https://github.com/fulstock/Learning-from-Flat-Annotations.
%U https://aclanthology.org/2026.eacl-srw.50/
%P 649-663
Markdown (Informal)
[Learning Nested Named Entity Recognition from Flat Annotations](https://aclanthology.org/2026.eacl-srw.50/) (Rozhkov & Loukachevitch, EACL 2026)
ACL
- Igor Rozhkov and Natalia V Loukachevitch. 2026. Learning Nested Named Entity Recognition from Flat Annotations. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 649–663, Rabat, Morocco. Association for Computational Linguistics.