---
title: "AAbAAC — paper by Maury et al. (2026) · BioNLP 2026"
description: "Autoimmune diseases affect a sizeable share of the population, but many are individually rare. 27 references."
authors: ["Fabien Maury", "Solène Grosdidier", "Maud de Dieuleveult", "Adrien Coulet"]
year: 2026
venue: "BioNLP 2026"
source: "https://aclanthology.org/2026.bionlp-1.65/"
doi: "10.18653/v1/2026.bionlp-1.65"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/maury-2026-aabaac-annotated-corpus-autoimmunity-information/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/maury-2026-aabaac-annotated-corpus-autoimmunity-information/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/) / AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction

# AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction

**Authors:** Fabien Maury, Solène Grosdidier, Maud de Dieuleveult and Adrien Coulet · **Year:** 2026 · **Venue:** [BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/) ([BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.bionlp-1.65/) · [PDF](https://aclanthology.org/2026.bionlp-1.65.pdf) · [DOI 10.18653/v1/2026.bionlp-1.65](https://doi.org/10.18653/v1/2026.bionlp-1.65) · [OpenAlex](https://openalex.org/W7166806521)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Autoimmune diseases affect a sizeable share of the population, but many are individually rare. Knowledge about them and their autoantibodies is spread across the literature, and no manually annotated corpus has existed for training or evaluating extraction tools in this niche. The authors built AAbAAC (AutoAntibodies and Autoimmunity Annotated Corpus) from PubMed titles and abstracts. They first compiled a dictionary of autoantibody names, with generated lexical variants, from HPO terms. They then retrieved candidate papers through MeSH-filtered queries and narrowed them using dictionary matches and GLiNER pre-annotations. A random sample of 115 texts was double-annotated in Doccano by four annotators, and a head annotator adjudicated the result. The annotations cover five entity types and ten relation types. In NER experiments, GLiNER and MedGemma models fine-tuned on AAbAAC outperformed a dictionary baseline as well as zero- and few-shot use of the same models. The work shows that a modest annotation effort can meaningfully improve extraction in a specialized biomedical area. It also provides a starting point for future relation-extraction work on autoimmunity.

## Key points
- **Dictionary and retrieval:** The dictionary contains 10,916 name variants for 285 autoantibodies, derived from HPO release 2024-07-01. PubMed queries returned 56,750 abstracts, and filtering reduced these to 44,890 candidates.
- **Sampling:** 120 texts were sampled for annotation. Five were discarded as off-topic or not in English, leaving 115.
- **Annotation scheme:** Five entity types are annotated: the autoantibodies themselves (Autoantibody), the molecules they bind (Autoantibody target), where they are found (Autoantibody location), associated conditions (Disease), and clinical manifestations (Symptom or clinical sign). Ten relation types are annotated, including is associated with, is target of, and is synonym of. The corpus contains 1,779 relations in total, with 735 isAssociatedWith and 494 isTargetOf.
- **Annotation process:**
  - Each text was annotated by two of four annotators, using balanced annotator pairings.
  - Entity pre-annotations came from string matching and the biomedical GLiNER model `urchade/gliner_large_bio-v0.1`.
  - Obvious relations between nested entities were added automatically after manual annotation.
- **Limitations and release:**
  - Relation extraction has not yet been evaluated.
  - Some relation types are very sparse, such as isCausedBy (13) and isRefTo (2).
  - The corpus is available at github.com/f-maury/AAbAAC.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Institut national de recherche en sciences et technologies du numérique](https://md.research.elamur.ai/free/en/labs/institut-national-de-recherche-en-sciences-et-technologies-du-numerique/) — Research institute, Le Chesnay-Rocquencourt, France · 84 works · 25,414 citations
- [Université Paris Cité](https://md.research.elamur.ai/free/en/universities/universite-paris-cite/) — University, Paris, France · 19 works · 1,426 citations
- [Inserm](https://md.research.elamur.ai/free/en/labs/inserm/) — Research institute, Paris, France · 6 works · 462 citations
- [Heka : Méthodes basées sur les données et modèles en santé pour l'acquisition de connaissances](https://md.research.elamur.ai/free/en/labs/heka-methodes-basees-sur-les-donnees-et-modeles-en-sante-pour-l-acquisition-de/) — Research institute, Paris, France · 2 works · 256 citations

Also on the byline: [Institut des Maladies Génétiques Imagine](https://ror.org/05rq3rb55).

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 234 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 231 works

🧭 Topics (1): [🔎 Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/) · 167 works

## Cite

Cite as: Fabien Maury, Solène Grosdidier, Maud de Dieuleveult and Adrien Coulet. 2026. AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction. BioNLP 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{maury2026aabaac,
  title = {{AAbAAC: An Annotated Corpus for Autoimmunity Information Extraction}},
  author = {Fabien Maury, Solène Grosdidier, Maud {de Dieuleveult} and Adrien Coulet},
  booktitle = {BioNLP 2026},
  year = {2026},
  doi = {10.18653/v1/2026.bionlp-1.65},
  url = {https://doi.org/10.18653/v1/2026.bionlp-1.65}
}
```

- [← previous AAA at SemEval-2026 Task 10: Psycholinguistic Conspiracy Marker Extraction and Detection](https://md.research.elamur.ai/free/en/papers/pan-2026-aaa-semeval-2026-task-10/)
- [next → Abjad AI at KSAA-2026 Shared Task 2: Grouped Speech Conditioning for Arabic Diacritization](https://md.research.elamur.ai/free/en/papers/alharthi-2026-abjad-ai-ksaa-2026-shared/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/)

## References

27 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Haseeb Ahsan. 2023. Origins and history of autoimmunity—A brief review. Rheumatology & Autoimmunity, 3(1):9–14. [find](https://scholar.google.com/scholar?q=Haseeb+Ahsan%2E+2023%2E+Origins+and+history+of+autoimmunity%E2%80%94A+brief+review%2E+Rheumatology+%26+Autoimmunity%2C+3%281%29%3A9%E2%80%9314%2E)
2. Olivier Bodenreider. 2004. The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Research, 32(Database issue):D267. [find](https://scholar.google.com/scholar?q=Olivier+Bodenreider%2E+2004%2E+The+Unified+Medical+Language+System+%28UMLS%29%3A+integrating+biomedical+terminology%2E+Nucleic+Acids+Research%2C+32%28Database+issue%29%3AD267%2E)
3. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
4. Thuy Trang Dinh, Trang Phuong Vo-Chanh, Chau Nguyen, Viet Quoc Huynh, Nam Vo, and Hoang Duc Nguyen. 2022. Extract antibody and antigen names from biomedical literature. BMC Bioinformatics, 23:524. [find](https://scholar.google.com/scholar?q=Thuy+Trang+Dinh%2C+Trang+Phuong+Vo%2DChanh%2C+Chau+Nguyen%2C+Viet+Quoc+Huynh%2C+Nam+Vo%2C+and+Hoang+Duc+Nguyen%2E+2022%2E+Extract+antibody+and+antigen+names+from+biomedical+literature%2E+BMC+Bioinformatics%2C+23%3A524%2E)
5. A. W. Forrey, C. J. McDonald, G. DeMoor, S. M. Huff, D. Leavelle, D. Leland, T. Fiers, L. Charles, B. Griffin, F. Stalling, A. Tullis, K. Hutchins, and J. Baen-ziger. 1996. Logical observation identifier names and codes (LOINC) database: a public use set of codes and names for electronic reporting o… [find](https://scholar.google.com/scholar?q=A%2E+W%2E+Forrey%2C+C%2E+J%2E+McDonald%2C+G%2E+DeMoor%2C+S%2E+M%2E+Huff%2C+D%2E+Leavelle%2C+D%2E+Leland%2C+T%2E+Fiers%2C+L%2E+Charles%2C+B%2E+Griffin%2C+F%2E+Stalling%2C+A%2E+Tullis%2C+K%2E+Hutchins%2C+and+J%2E+Baen%2Dziger%2E+1996%2E+Logical+observation+identif)
6. Michael A. Gargano, Nicolas Matentzoglu, Ben Coleman, Eunice B. Addo-Lartey, Anna V. Anagnostopoulos, Joel Anderton, Paul Avillach, Anita M. Bagley, Eduard Bakštein, James P. Balhoff, Gareth Baynam, Susan M. Bello, Michael Berk, Holli Bertram, Somer Bishop, Hannah Blau, David F. Bodenstein, Pablo Bo… [find](https://scholar.google.com/scholar?q=Michael+A%2E+Gargano%2C+Nicolas+Matentzoglu%2C+Ben+Coleman%2C+Eunice+B%2E+Addo%2DLartey%2C+Anna+V%2E+Anagnostopoulos%2C+Joel+Anderton%2C+Paul+Avillach%2C+Anita+M%2E+Bagley%2C+Eduard+Bak%C5%A1tein%2C+James+P%2E+Balhoff%2C+Gareth+Baynam%2C+S)
7. Yu Gu, Robert Tinn, Hao Cheng, Michael Lucas, Naoto Usuyama, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, and Hoifung Poon. 2022. [Domain-specific language model pretraining for biomedical natural language processing](https://md.research.elamur.ai/free/en/papers/gu-2020-domain-specific-language-model-pretraining/). ACM Transactions on Computing for Healthcare, 3(1):1–23.
8. Scott M. Hayter and Matthew C. Cook. 2012. Updated assessment of the prevalence, spectrum and case definition of autoimmune disease. Autoimmunity Reviews, 11(10):754–765. [find](https://scholar.google.com/scholar?q=Scott+M%2E+Hayter+and+Matthew+C%2E+Cook%2E+2012%2E+Updated+assessment+of+the+prevalence%2C+spectrum+and+case+definition+of+autoimmune+disease%2E+Autoimmunity+Reviews%2C+11%2810%29%3A754%E2%80%93765%2E)
9. Eduard Hovy and Julia Lavid. 2010. Towards a ‘science’ of corpus annotation: A new methodological challenge for corpus linguistics. Open Journal of Modern Linguistics, 9(3):206–214. [find](https://scholar.google.com/scholar?q=Eduard+Hovy+and+Julia+Lavid%2E+2010%2E+Towards+a+%E2%80%98science%E2%80%99+of+corpus+annotation%3A+A+new+methodological+challenge+for+corpus+linguistics%2E+Open+Journal+of+Modern+Linguistics%2C+9%283%29%3A206%E2%80%93214%2E)
10. Yann Mathet, Antoine Widlöcher, and Jean-Philippe Métivier. 2015. The unified and holistic method gamma (γ) for inter-annotator agreement measure and alignment. Computational Linguistics, 41(3):437–479. [find](https://scholar.google.com/scholar?q=Yann+Mathet%2C+Antoine+Widl%C3%B6cher%2C+and+Jean%2DPhilippe+M%C3%A9tivier%2E+2015%2E+The+unified+and+holistic+method+gamma+%28%CE%B3%29+for+inter%2Dannotator+agreement+measure+and+alignment%2E+Computational+Linguistics%2C+41%283%29%3A437%E2%80%9347)
11. Frederick W. Miller. 2023. The increasing prevalence of autoimmunity and autoimmune diseases: An urgent call to action for improved understanding, diagnosis, treatment and prevention. Current opinion in immunology, 80(102266). [find](https://scholar.google.com/scholar?q=Frederick+W%2E+Miller%2E+2023%2E+The+increasing+prevalence+of+autoimmunity+and+autoimmune+diseases%3A+An+urgent+call+to+action+for+improved+understanding%2C+diagnosis%2C+treatment+and+prevention%2E+Current+opinion+)
12. Sunil Mohan and Donghui Li. 2019. Medmentions: A large biomedical corpus annotated with UMLS concepts. In 1st Conference on Automated Knowledge Base Construction, AKBC 2019, Amherst, MA, USA, May 20-22, 2019. [find](https://scholar.google.com/scholar?q=Sunil+Mohan+and+Donghui+Li%2E+2019%2E+Medmentions%3A+A+large+biomedical+corpus+annotated+with+UMLS+concepts%2E+In+1st+Conference+on+Automated+Knowledge+Base+Construction%2C+AKBC+2019%2C+Amherst%2C+MA%2C+USA%2C+May+20%2D2)
13. Marco Naguib, Xavier Tannier, and Aurélie Névéol. 2024. Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6829–6852, Miami, Florida, USA. A… [find](https://scholar.google.com/scholar?q=Marco+Naguib%2C+Xavier+Tannier%2C+and+Aur%C3%A9lie+N%C3%A9v%C3%A9ol%2E+2024%2E+Few%2Dshot+clinical+entity+recognition+in+English%2C+French+and+Spanish%3A+masked+language+models+outperform+generative+model+prompting%2E+In+Findings+o)
14. Hiroki Nakayama, Takahiro Kubo, Junya Kamura, Yasufumi Taniguchi, and Xu Liang. 2018. doccano: Text annotation tool for human. Software available from [https://github.com/doccano/doccano](https://github.com/doccano/doccano). [↗](https://github.com/doccano/doccano)
15. Ana Rath, Annie Olry, Ferdinand Dhombres, Maja Miličić Brandt, Bruno Urbero, and Segolene Ayme. 2012. Representation of rare diseases in health information systems: The orphanet approach to serve a wide range of end users. Human Mutation, 33(5):803–808. [find](https://scholar.google.com/scholar?q=Ana+Rath%2C+Annie+Olry%2C+Ferdinand+Dhombres%2C+Maja+Milic%CC%8Cic%CC%81+Brandt%2C+Bruno+Urbero%2C+and+Segolene+Ayme%2E+2012%2E+Representation+of+rare+diseases+in+health+information+systems%3A+The+orphanet+approach+to+serve+a+)
16. Adam Remaki, Jacques Ung, Pierre Pages, Perceval Wajsburt, Elise Liu, Guillaume Faure, Thomas Petit-Jean, Xavier Tannier, and Christel Gérardin. 2025. Improving Phenotyping of Patients With Immune-Mediated Inflammatory Diseases Through Automated Processing of Discharge Summaries: Multicenter Cohort… [find](https://scholar.google.com/scholar?q=Adam+Remaki%2C+Jacques+Ung%2C+Pierre+Pages%2C+Perceval+Wajsburt%2C+Elise+Liu%2C+Guillaume+Faure%2C+Thomas+Petit%2DJean%2C+Xavier+Tannier%2C+and+Christel+G%C3%A9rardin%2E+2025%2E+Improving+Phenotyping+of+Patients+With+Immune%2DMed)
17. Eric Sayers. 2018. E-utilities quick start. In Entrez® Programming Utilities Help [Internet]. National Center for Biotechnology Information (US). [find](https://scholar.google.com/scholar?q=Eric+Sayers%2E+2018%2E+E%2Dutilities+quick+start%2E+In+Entrez%C2%AE+Programming+Utilities+Help+%5BInternet%5D%2E+National+Center+for+Biotechnology+Information+%28US%29%2E)
18. Yinon Shapira, Nancy Agmon-Levin, and Yehuda Shoenfeld. 2010. Defining and analyzing geoepi-demiology and human autoimmunity. Journal of Autoimmunity, 34(3):J168–J177. [find](https://scholar.google.com/scholar?q=Yinon+Shapira%2C+Nancy+Agmon%2DLevin%2C+and+Yehuda+Shoenfeld%2E+2010%2E+Defining+and+analyzing+geoepi%2Ddemiology+and+human+autoimmunity%2E+Journal+of+Autoimmunity%2C+34%283%29%3AJ168%E2%80%93J177%2E)
19. Luca Soldaini and Nazli Goharian. 2016. Quickumls: a fast, unsupervised approach for medical concept extraction. In MedIR workshop, sigir, pages 1–4. [find](https://scholar.google.com/scholar?q=Luca+Soldaini+and+Nazli+Goharian%2E+2016%2E+Quickumls%3A+a+fast%2C+unsupervised+approach+for+medical+concept+extraction%2E+In+MedIR+workshop%2C+sigir%2C+pages+1%E2%80%934%2E)
20. Sandeep Subramanian and Madhavi K. Ganapathiraju. 2017. Antibody exchange: Information extraction of biological antibody donation and a web-portal to find donors and seekers. Data, 2(4):38. [find](https://scholar.google.com/scholar?q=Sandeep+Subramanian+and+Madhavi+K%2E+Ganapathiraju%2E+2017%2E+Antibody+exchange%3A+Information+extraction+of+biological+antibody+donation+and+a+web%2Dportal+to+find+donors+and+seekers%2E+Data%2C+2%284%29%3A38%2E)
21. Hadrien Titeux and Rachid Riad. 2021. pygamma-agreement: Gamma γ measure for inter/intra-annotator agreement in python. Journal of Open Source Software, 6(62):2989. [find](https://scholar.google.com/scholar?q=Hadrien+Titeux+and+Rachid+Riad%2E+2021%2E+pygamma%2Dagreement%3A+Gamma+%CE%B3+measure+for+inter%2Fintra%2Dannotator+agreement+in+python%2E+Journal+of+Open+Source+Software%2C+6%2862%29%3A2989%2E)
22. Randi Vita, Nina Blazeska, Daniel Marrama, IEDB Curation Team Members, Sebastian Duesing, Jason Bennett, Jason Greenbaum, Marcus De Almeida Mendes, Jarjapu Mahita, Daniel K. Wheeler, Jason R. Cantrell, James A. Overton, Darren A. Natale, Alessandro Sette, and Bjoern Peters. 2025. The immune epitope… [find](https://scholar.google.com/scholar?q=Randi+Vita%2C+Nina+Blazeska%2C+Daniel+Marrama%2C+IEDB+Curation+Team+Members%2C+Sebastian+Duesing%2C+Jason+Bennett%2C+Jason+Greenbaum%2C+Marcus+De+Almeida+Mendes%2C+Jarjapu+Mahita%2C+Daniel+K%2E+Wheeler%2C+Jason+R%2E+Cantrell)
23. Amy Y. Wang, Jeremiah H. Sable, and Kent A. Spackman. 2002. The SNOMED clinical terms development process: refinement and analysis of content. Proceedings of the AMIA Symposium, pages 845– 849. [find](https://scholar.google.com/scholar?q=Amy+Y%2E+Wang%2C+Jeremiah+H%2E+Sable%2C+and+Kent+A%2E+Spackman%2E+2002%2E+The+SNOMED+clinical+terms+development+process%3A+refinement+and+analysis+of+content%2E+Proceedings+of+the+AMIA+Symposium%2C+pages+845%E2%80%93+849%2E)
24. Dan Wang, Liuhui Yang, Ping Zhang, Joshua LaBaer, Henning Hermjakob, Dong Li, and Xiaobo Yu. 2017. AAgAtlas 1.0: a human autoantigen database. Nucleic Acids Research, 45(D1):D769–D776. [find](https://scholar.google.com/scholar?q=Dan+Wang%2C+Liuhui+Yang%2C+Ping+Zhang%2C+Joshua+LaBaer%2C+Henning+Hermjakob%2C+Dong+Li%2C+and+Xiaobo+Yu%2E+2017%2E+AAgAtlas+1%2E0%3A+a+human+autoantigen+database%2E+Nucleic+Acids+Research%2C+45%28D1%29%3AD769%E2%80%93D776%2E)
25. Anthony Yazdani, Ihor Stepanov, and Douglas Teodoro. 2025. Gliner-biomed: A suite of efficient models for open biomedical named entity recognition. arXiv preprint arXiv:2504.00676. — [arXiv:2504.00676](https://arxiv.org/abs/2504.00676) [find](https://scholar.google.com/scholar?q=Anthony+Yazdani%2C+Ihor+Stepanov%2C+and+Douglas+Teodoro%2E+2025%2E+Gliner%2Dbiomed%3A+A+suite+of+efficient+models+for+open+biomedical+named+entity+recognition%2E+arXiv+preprint+arXiv%3A2504%2E00676%2E+%E2%80%94+%5BarXiv%3A2504%2E00676)
26. Urchade Zaratiana, Gil Pasternak, Oliver Boyd, George Hurn-Maloney, and Ash Lewis. 2025. GLiNER2: Schema-driven multi-task learning for structured information extraction. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 130–140.… [find](https://scholar.google.com/scholar?q=Urchade+Zaratiana%2C+Gil+Pasternak%2C+Oliver+Boyd%2C+George+Hurn%2DMaloney%2C+and+Ash+Lewis%2E+2025%2E+GLiNER2%3A+Schema%2Ddriven+multi%2Dtask+learning+for+structured+information+extraction%2E+In+Proceedings+of+the+2025+Co)
27. Urchade Zaratiana, Nadi Tomeh, Pierre Holat, and Thierry Charnois. 2024. [GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer](https://md.research.elamur.ai/free/en/papers/zaratiana-2024-gliner-generalist-model-named-entity/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technol…

*Updated 1 November 2026*