---
title: "An Extreme Multi-label Text Classification — D'Souza 2026"
description: "Manual subject indexing in libraries is hard to scale as catalogs grow and become more multilingual."
authors: ["Jennifer D'Souza", "Sameer Sadruddin", "Maximilian Kaehler", "Andrea Salfinger", "Luca Zaccagna", "Francesca Incitti", "Lauro Snidaro", "Osma Suominen"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.12/"
doi: "10.63317/5kag6gjg636f"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/souza-2026-extreme-multi-label-text-classification/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/souza-2026-extreme-multi-label-text-classification/)

[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/) / An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took “Use of Practical AI in Digital Libraries” Seriously?

# An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took “Use of Practical AI in Digital Libraries” Seriously?

**Authors:** Jennifer D'Souza, Sameer Sadruddin, Maximilian Kaehler, Andrea Salfinger, Luca Zaccagna, Francesca Incitti, Lauro Snidaro, Osma Suominen · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.12/) · [PDF](https://aclanthology.org/2026.lrec-1.12.pdf) · [DOI 10.63317/5kag6gjg636f](https://doi.org/10.63317/5kag6gjg636f) · [OpenAlex](https://openalex.org/W7160017281)

**Citations:** 1 citations (openalex-snapshot · 2026-10-14) · 1 in our library, of the 140673 papers whose bibliographies we read

## Summary
Manual subject indexing in libraries is hard to scale as catalogs grow and become more multilingual. Generic XMTC benchmarks such as Wiki-500K or EurLex-4K use flat or ad hoc labels and do not reflect real cataloging practice. Library linked-data releases, in turn, usually lack standard train/test splits. The authors address this gap with TIB-SID (TIB Subject Indexing Dataset). It contains about 136k English and German catalog records from the open TIBKAT dump of the TIB, each annotated with subject terms from the German Integrated Authority File (GND). The records come with predefined train/dev/test splits and a JSON (and SKOS-exportable) version of the GND subject taxonomy. The paper profiles the dataset statistically and runs qualitative, expert-based error analyses of three indexing systems. A key finding is that rare and zero-shot subjects remain the main weakness, especially for models trained per label. Because every prediction is tied to an authority vocabulary that libraries already use, the resource supports reproducible, ontology-aware evaluation. It also gives a basis for building AI assistants that help catalogers rather than replace them.

## Key points
- **Released resources:** TIB-SID is available on GitHub under CC BY 4.0. It includes 207,001 GND Sachbegriff subjects converted from MARC 21 to JSON. Field coverage varies: about half of the subjects have alternate names, 80% have related subjects, and 27% have definitions.
- **Source data:** The corpus comes from an open TIBKAT dump of roughly 200k records released under CC0. Language detection with langdetect found 48 languages, dominated by German (108,637 records) and English (76,735).
- **Systems evaluated:**
  - System 1 matches document text to GND subjects via embeddings.
  - System 2 generates candidate subjects with an LLM and maps them to the GND.
  - System 3 is an ensemble of Omikuji, XTransformer and MLLM.
- **System 2 errors:** In a sample of 43 truly wrong suggestions, 11 were classified as MEU and 5 as MEA. These errors arise when the LLM proposes concepts that the GND lacks, such as "Spoofing" or "Luftfahrtradar", which then get matched to the wrong entities.
- **System 3 errors:** The analysis found 61 missed-aspect cases (FNM), of which 25 appeared in the top-20 but not the top-5 (FNM5), plus 9 FNC cases. False negatives dominate for subjects with low training-set frequency.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cite

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

```bibtex
@inproceedings{dsouza2026extreme,
  title = {{An Extreme Multi-label Text Classification (XMTC) Library Dataset: What If We Took “Use of Practical AI in Digital Libraries” Seriously?}},
  author = {D'Souza, Jennifer and Sadruddin, Sameer and Kaehler, Maximilian and Salfinger, Andrea and Zaccagna, Luca and Incitti, Francesca and Snidaro, Lauro and Suominen, Osma},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5kag6gjg636f},
  url = {https://doi.org/10.63317/5kag6gjg636f}
}
```

- [← previous AMIYA Shared Task: Arabic Modeling In Your Accent at VarDial 2026](https://md.research.elamur.ai/free/en/papers/robinson-2026-amiya-shared-task-arabic-modeling/)
- [next → Anchoring the Judge: Curriculum-Based Adaptation and Reference-Anchored MQM for LLM-Based Machine Translation of an Unseen Low-Resource Language - A Case of Nupe](https://md.research.elamur.ai/free/en/papers/umar-2026-anchoring-judge-curriculum-based-adaptation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/)

## References

62 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anila Angjeli, Emmanuelle Bermès, Dean Birkett, Maarten Brinkerink, Valentine Charles, Mariana Damova, Cécile Devarenne, Maria Gäde, Sergiu Gordea, David Haskiya, Timothy Hill, Antoine Isaac, Lukas Koster, Hugo Manguinhas, Gregory Markus, Mark A. Matienzo, and Vivien Petras. 2016. White paper on bes… [find](https://scholar.google.com/scholar?q=Anila+Angjeli%2C+Emmanuelle+Berm%C3%A8s%2C+Dean+Birkett%2C+Maarten+Brinkerink%2C+Valentine+Charles%2C+Mariana+Damova%2C+C%C3%A9cile+Devarenne%2C+Maria+G%C3%A4de%2C+Sergiu+Gordea%2C+David+Haskiya%2C+Timothy+Hill%2C+Antoine+Isaac%2C+Lukas+Ko)
2. Hamed Babaei Giglou, Jennifer D’Souza, Oliver Karras, and Sören Auer. 2025. Ontoaligner: A comprehensive modular and robust python toolkit for ontology alignment. In European Semantic Web Conference, pages 174–191. Springer. [find](https://scholar.google.com/scholar?q=Hamed+Babaei+Giglou%2C+Jennifer+D%E2%80%99Souza%2C+Oliver+Karras%2C+and+S%C3%B6ren+Auer%2E+2025%2E+Ontoaligner%3A+A+comprehensive+modular+and+robust+python+toolkit+for+ontology+alignment%2E+In+European+Semantic+Web+Conference%2C+)
3. Rohit Babbar and Bernhard Schölkopf. 2017. Dismec: Distributed sparse machines for extreme multi-label classification. In Proceedings of the tenth ACM international conference on web search and data mining, pages 721–729. [find](https://scholar.google.com/scholar?q=Rohit+Babbar+and+Bernhard+Sch%C3%B6lkopf%2E+2017%2E+Dismec%3A+Distributed+sparse+machines+for+extreme+multi%2Dlabel+classification%2E+In+Proceedings+of+the+tenth+ACM+international+conference+on+web+search+and+data+m)
4. K. Bhatia, K. Dahiya, H. Jain, P. Kar, A. Mittal, Y. Prabhu, and M. Varma. 2016. The extreme classification repository: Multi-label datasets and code. [find](https://scholar.google.com/scholar?q=K%2E+Bhatia%2C+K%2E+Dahiya%2C+H%2E+Jain%2C+P%2E+Kar%2C+A%2E+Mittal%2C+Y%2E+Prabhu%2C+and+M%2E+Varma%2E+2016%2E+The+extreme+classification+repository%3A+Multi%2Dlabel+datasets+and+code%2E)
5. Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, and Prateek Jain. 2015. Sparse local embeddings for extreme multi-label classification. Advances in neural information processing systems, 28. [find](https://scholar.google.com/scholar?q=Kush+Bhatia%2C+Himanshu+Jain%2C+Purushottam+Kar%2C+Manik+Varma%2C+and+Prateek+Jain%2E+2015%2E+Sparse+local+embeddings+for+extreme+multi%2Dlabel+classification%2E+Advances+in+neural+information+processing+systems%2C+28%2E)
6. Kathi Canese and Sarah Weis. 2013. Pubmed: the bibliographic database. The NCBI handbook, 2(1):2013. [find](https://scholar.google.com/scholar?q=Kathi+Canese+and+Sarah+Weis%2E+2013%2E+Pubmed%3A+the+bibliographic+database%2E+The+NCBI+handbook%2C+2%281%29%3A2013%2E)
7. Caterina Caracciolo, Armando Stellato, Ahsan Morshed, Gudrun Johannsen, Sachit Rajbhandari, Yves Jaques, and Johannes Keizer. 2013. The agrovoc linked dataset. Semantic Web, 4(3):341– 348. [find](https://scholar.google.com/scholar?q=Caterina+Caracciolo%2C+Armando+Stellato%2C+Ahsan+Morshed%2C+Gudrun+Johannsen%2C+Sachit+Rajbhandari%2C+Yves+Jaques%2C+and+Johannes+Keizer%2E+2013%2E+The+agrovoc+linked+dataset%2E+Semantic+Web%2C+4%283%29%3A341%E2%80%93+348%2E)
8. Wei-Cheng Chang, Hsiang-Fu Yu, Kai Zhong, Yiming Yang, and Inderjit S Dhillon. 2020. Taming pretrained transformers for extreme multi-label text classification. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pages 3163– 3171. [find](https://scholar.google.com/scholar?q=Wei%2DCheng+Chang%2C+Hsiang%2DFu+Yu%2C+Kai+Zhong%2C+Yiming+Yang%2C+and+Inderjit+S+Dhillon%2E+2020%2E+Taming+pretrained+transformers+for+extreme+multi%2Dlabel+text+classification%2E+In+Proceedings+of+the+26th+ACM+SIGKDD+i)
9. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216. [find](https://scholar.google.com/scholar?q=Jianlv+Chen%2C+Shitao+Xiao%2C+Peitian+Zhang%2C+Kun+Luo%2C+Defu+Lian%2C+and+Zheng+Liu%2E+2024%2E+Bge+m3%2Dembedding%3A+Multi%2Dlingual%2C+multi%2Dfunctionality%2C+multi%2Dgranularity+text+embeddings+through+self%2Dknowledge+distill) [our card](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/)
10. Corine Deliot. 2014. Publishing the british national bibliography as linked open data. Catalogue & Index, 174:13–18. [find](https://scholar.google.com/scholar?q=Corine+Deliot%2E+2014%2E+Publishing+the+british+national+bibliography+as+linked+open+data%2E+Catalogue+%26+Index%2C+174%3A13%E2%80%9318%2E)
11. Maria Dermentzi, Mike Bryant, Herminio García-González, and Fabio Rovigo. 2025a. Ehri multilingual subject indexing test dataset. [find](https://scholar.google.com/scholar?q=Maria+Dermentzi%2C+Mike+Bryant%2C+Herminio+Garc%C3%ADa%2DGonz%C3%A1lez%2C+and+Fabio+Rovigo%2E+2025a%2E+Ehri+multilingual+subject+indexing+test+dataset%2E)
12. Maria Dermentzi, Mike Bryant, Fabio Rovigo, and Herminio García-González. 2025b. Multilingual Automated Subject Indexing: a comparative study of LLMs vs alternative approaches in the context of the EHRI project. Working paper or preprint. [find](https://scholar.google.com/scholar?q=Maria+Dermentzi%2C+Mike+Bryant%2C+Fabio+Rovigo%2C+and+Herminio+Garc%C3%ADa%2DGonz%C3%A1lez%2E+2025b%2E+Multilingual+Automated+Subject+Indexing%3A+a+comparative+study+of+LLMs+vs+alternative+approaches+in+the+context+of+the+EH)
13. Aleksei Dorkin and Kairit Sirts. 2025. Tartunlp at semeval-2025 task 5: Subject tagging as two-stage information retrieval. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2449–2454. [find](https://scholar.google.com/scholar?q=Aleksei+Dorkin+and+Kairit+Sirts%2E+2025%2E+Tartunlp+at+semeval%2D2025+task+5%3A+Subject+tagging+as+two%2Dstage+information+retrieval%2E+In+Proceedings+of+the+19th+International+Workshop+on+Semantic+Evaluation+%28Se)
14. Jennifer D’Souza, Sameer Sadruddin, Holger Israel, Mathias Begoin, and Diana Slawig. 2025. SemEval-2025 task 5: LLMs4Subjects - LLM-based automated subject tagging for a national technical library’s open-access catalog. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEva… [find](https://scholar.google.com/scholar?q=Jennifer+D%E2%80%99Souza%2C+Sameer+Sadruddin%2C+Holger+Israel%2C+Mathias+Begoin%2C+and+Diana+Slawig%2E+2025%2E+SemEval%2D2025+task+5%3A+LLMs4Subjects+%2D+LLM%2Dbased+automated+subject+tagging+for+a+national+technical+library%E2%80%99s+o)
15. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv e-prints, pages arXiv– 2407. [find](https://scholar.google.com/scholar?q=Abhimanyu+Dubey%2C+Abhinav+Jauhri%2C+Abhinav+Pandey%2C+Abhishek+Kadian%2C+Ahmad+Al%2DDahle%2C+Aiesha+Letman%2C+Akhil+Mathur%2C+Alan+Schelten%2C+Amy+Yang%2C+Angela+Fan%2C+et+al%2E+2024%2E+The+llama+3+herd+of+models%2E+arXiv+e%2Dpri)
16. FAO. 2023. Introducing agris 2.0! Online news article. Accessed: \\<add your access date\>. [find](https://scholar.google.com/scholar?q=FAO%2E+2023%2E+Introducing+agris+2%2E0%21+Online+news+article%2E+Accessed%3A+%5C%3Cadd+your+access+date%5C%3E%2E)
17. Luis Gasco, Anastasios Nentidis, Anastasia Krithara, Darryl Estrada-Zavala, Renato Toshiyuki Murasaki, Elena Primo-Peña, Cristina Bojo Canales, Georgios Paliouras, Martin Krallinger, et al. 2021. Overview of bioasq 2021-mesinesp track. evaluation of advance hierarchical classification techniques for… [find](https://scholar.google.com/scholar?q=Luis+Gasco%2C+Anastasios+Nentidis%2C+Anastasia+Krithara%2C+Darryl+Estrada%2DZavala%2C+Renato+Toshiyuki+Murasaki%2C+Elena+Primo%2DPe%C3%B1a%2C+Cristina+Bojo+Canales%2C+Georgios+Paliouras%2C+Martin+Krallinger%2C+et+al%2E+2021%2E+Over)
18. Jim Hahn. 2025. Jim at semeval-2025 task 5: Multilingual bert ensemble. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2407–2412. [find](https://scholar.google.com/scholar?q=Jim+Hahn%2E+2025%2E+Jim+at+semeval%2D2025+task+5%3A+Multilingual+bert+ensemble%2E+In+Proceedings+of+the+19th+International+Workshop+on+Semantic+Evaluation+%28SemEval%2D2025%29%2C+pages+2407%E2%80%932412%2E)
19. Clara Wan Ching Ho. 2025. UBFFM at the GermEval-2025 LLMs4Subjects task: What if we take “you are an expert in subject indexing” seriously? In Proceedings of the 21st Conference on Natural Language Processing (KON-VENS 2025): Workshops, pages 471–478, Hannover, Germany. HsH Applied Academics. [find](https://scholar.google.com/scholar?q=Clara+Wan+Ching+Ho%2E+2025%2E+UBFFM+at+the+GermEval%2D2025+LLMs4Subjects+task%3A+What+if+we+take+%E2%80%9Cyou+are+an+expert+in+subject+indexing%E2%80%9D+seriously%3F+In+Proceedings+of+the+21st+Conference+on+Natural+Language+Pr)
20. Antoine Isaac and Bernhard Haslhofer. 2013. Europeana linked open data–data. europeana. eu. Semantic Web, 4(3):291–297. [find](https://scholar.google.com/scholar?q=Antoine+Isaac+and+Bernhard+Haslhofer%2E+2013%2E+Europeana+linked+open+data%E2%80%93data%2E+europeana%2E+eu%2E+Semantic+Web%2C+4%283%29%3A291%E2%80%93297%2E)
21. Baharul Islam, Nasim Ahmad, Ferdous Barbhuiya, and Kuntal Dey. 2025. Nbf at semeval-2025 task 5: Light-burst attention enhanced system for multilingual subject recommendation. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 953– 958. [find](https://scholar.google.com/scholar?q=Baharul+Islam%2C+Nasim+Ahmad%2C+Ferdous+Barbhuiya%2C+and+Kuntal+Dey%2E+2025%2E+Nbf+at+semeval%2D2025+task+5%3A+Light%2Dburst+attention+enhanced+system+for+multilingual+subject+recommendation%2E+In+Proceedings+of+the+19)
22. Paul Jaccard. 1912. The distribution of the flora in the alpine zone. 1. New phytologist, 11(2):37–50. [find](https://scholar.google.com/scholar?q=Paul+Jaccard%2E+1912%2E+The+distribution+of+the+flora+in+the+alpine+zone%2E+1%2E+New+phytologist%2C+11%282%29%3A37%E2%80%9350%2E)
23. Kalervo Järvelin and Jaana Kekäläinen. 2002. Cumulated gain-based evaluation of ir techniques. ACM Transactions on Information Systems (TOIS), 20(4):422–446. [find](https://scholar.google.com/scholar?q=Kalervo+J%C3%A4rvelin+and+Jaana+Kek%C3%A4l%C3%A4inen%2E+2002%2E+Cumulated+gain%2Dbased+evaluation+of+ir+techniques%2E+ACM+Transactions+on+Information+Systems+%28TOIS%29%2C+20%284%29%3A422%E2%80%93446%2E)
24. Hong Jiang, Jin Wang, and Xuejie Zhang. 2025. Ynu-hpcc at semeval-2025 task 5: Contrastive learning for gnd subject tagging with multilingual sentence-bert. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2443–2448. [find](https://scholar.google.com/scholar?q=Hong+Jiang%2C+Jin+Wang%2C+and+Xuejie+Zhang%2E+2025%2E+Ynu%2Dhpcc+at+semeval%2D2025+task+5%3A+Contrastive+learning+for+gnd+subject+tagging+with+multilingual+sentence%2Dbert%2E+In+Proceedings+of+the+19th+International+Wo)
25. Maximilian Kähler, Lisa Kluge, and Katja Konermann. 2025. DNB-AI-project at the GermEval-2025 LLMs4Subjects task: KIFSPrompt - knowledge-injected few-shot prompting. In Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025): Workshops, pages 455–464, Hannover, Germany. HsH… [find](https://scholar.google.com/scholar?q=Maximilian+K%C3%A4hler%2C+Lisa+Kluge%2C+and+Katja+Konermann%2E+2025%2E+DNB%2DAI%2Dproject+at+the+GermEval%2D2025+LLMs4Subjects+task%3A+KIFSPrompt+%2D+knowledge%2Dinjected+few%2Dshot+prompting%2E+In+Proceedings+of+the+21st+Confere)
26. Sujay Khandagale, Han Xiao, and Rohit Babbar. 2020. Bonsai: diverse and shallow trees for extreme multi-label classification. Machine Learning, 109(11):2099–2119. [find](https://scholar.google.com/scholar?q=Sujay+Khandagale%2C+Han+Xiao%2C+and+Rohit+Babbar%2E+2020%2E+Bonsai%3A+diverse+and+shallow+trees+for+extreme+multi%2Dlabel+classification%2E+Machine+Learning%2C+109%2811%29%3A2099%E2%80%932119%2E)
27. Anastasia Krithara, James G. Mork, Anastasios Nentidis, and Georgios Paliouras. 2023a. The road from manual to automatic semantic indexing of biomedical literature: a 10 years journey. Frontiers in Research Metrics and Analytics, 8. [find](https://scholar.google.com/scholar?q=Anastasia+Krithara%2C+James+G%2E+Mork%2C+Anastasios+Nentidis%2C+and+Georgios+Paliouras%2E+2023a%2E+The+road+from+manual+to+automatic+semantic+indexing+of+biomedical+literature%3A+a+10+years+journey%2E+Frontiers+in+Re)
28. Anastasia Krithara, Anastasios Nentidis, Konstantinos Bougiatiotis, and Georgios Paliouras. 2023b. Bioasq-qa: A manually curated corpus for biomedical question answering. Scientific Data, 10(1):170. [find](https://scholar.google.com/scholar?q=Anastasia+Krithara%2C+Anastasios+Nentidis%2C+Konstantinos+Bougiatiotis%2C+and+Georgios+Paliouras%2E+2023b%2E+Bioasq%2Dqa%3A+A+manually+curated+corpus+for+biomedical+question+answering%2E+Scientific+Data%2C+10%281%29%3A170%2E)
29. Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics, 22(1):79–86. [find](https://scholar.google.com/scholar?q=Solomon+Kullback+and+Richard+A+Leibler%2E+1951%2E+On+information+and+sufficiency%2E+The+annals+of+mathematical+statistics%2C+22%281%29%3A79%E2%80%9386%2E)
30. Jingzhou Liu, Wei-Cheng Chang, Yuexin Wu, and Yiming Yang. 2017. Deep learning for extreme multi-label text classification. In Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval, pages 115–124. [find](https://scholar.google.com/scholar?q=Jingzhou+Liu%2C+Wei%2DCheng+Chang%2C+Yuexin+Wu%2C+and+Yiming+Yang%2E+2017%2E+Deep+learning+for+extreme+multi%2Dlabel+text+classification%2E+In+Proceedings+of+the+40th+international+ACM+SIGIR+conference+on+research+an)
31. Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence, 42(4):824–836. [find](https://scholar.google.com/scholar?q=Yu+A+Malkov+and+Dmitry+A+Yashunin%2E+2018%2E+Efficient+and+robust+approximate+nearest+neighbor+search+using+hierarchical+navigable+small+world+graphs%2E+IEEE+transactions+on+pattern+analysis+and+machine+int) [our card](https://md.research.elamur.ai/free/en/papers/malkov-2016-efficient-robust-approximate-nearest-neighbor/)
32. Olena Medelyan. 2009. Human-competitive automatic topic indexing. Ph.D. thesis, The University of Waikato. [find](https://scholar.google.com/scholar?q=Olena+Medelyan%2E+2009%2E+Human%2Dcompetitive+automatic+topic+indexing%2E+Ph%2ED%2E+thesis%2C+The+University+of+Waikato%2E)
33. Isabelle Mohr, Markus Krimmel, Saba Sturua, Mohammad Kalim Akram, Andreas Koukounas, Michael Günther, Georgios Mastrapas, Vinit Ravishankar, Joan Fontanals Martínez, Feng Wang, et al. 2024. Multi-task contrastive learning for 8192-token bilingual text embeddings. arXiv preprint arXiv:2402.17016. — [arXiv:2402.17016](https://arxiv.org/abs/2402.17016) [find](https://scholar.google.com/scholar?q=Isabelle+Mohr%2C+Markus+Krimmel%2C+Saba+Sturua%2C+Mohammad+Kalim+Akram%2C+Andreas+Koukounas%2C+Michael+G%C3%BCnther%2C+Georgios+Mastrapas%2C+Vinit+Ravishankar%2C+Joan+Fontanals+Mart%C3%ADnez%2C+Feng+Wang%2C+et+al%2E+2024%2E+Multi%2Dtask)
34. NLM. 2000. Medical subject headings, volume 41. US Department of Health and Human Services, Public Health Service, National Library of Medicine. [find](https://scholar.google.com/scholar?q=NLM%2E+2000%2E+Medical+subject+headings%2C+volume+41%2E+US+Department+of+Health+and+Human+Services%2C+Public+Health+Service%2C+National+Library+of+Medicine%2E)
35. Hercules Panoutsopoulos and Christopher Brewster. 2022. Data-driven update of agrovoc using agricultural text corpora. In HAICTA, pages 260– 265. [find](https://scholar.google.com/scholar?q=Hercules+Panoutsopoulos+and+Christopher+Brewster%2E+2022%2E+Data%2Ddriven+update+of+agrovoc+using+agricultural+text+corpora%2E+In+HAICTA%2C+pages+260%E2%80%93+265%2E)
36. Karl Pearson. 1900. X. on the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science,… [find](https://scholar.google.com/scholar?q=Karl+Pearson%2E+1900%2E+X%2E+on+the+criterion+that+a+given+system+of+deviations+from+the+probable+in+the+case+of+a+correlated+system+of+variables+is+such+that+it+can+be+reasonably+supposed+to+have+arisen+fr)
37. Yashoteja Prabhu, Anil Kag, Shrutendra Harsola, Rahul Agrawal, and Manik Varma. 2018. Parabel: Partitioned label trees for extreme classification with application to dynamic search advertising. In Proceedings of the 2018 World Wide Web Conference, pages 993–1002. [find](https://scholar.google.com/scholar?q=Yashoteja+Prabhu%2C+Anil+Kag%2C+Shrutendra+Harsola%2C+Rahul+Agrawal%2C+and+Manik+Varma%2E+2018%2E+Parabel%3A+Partitioned+label+trees+for+extreme+classification+with+application+to+dynamic+search+advertising%2E+In+Pro)
38. Yashoteja Prabhu and Manik Varma. 2014. Fastxml: A fast, accurate and stable tree-classifier for extreme multi-label learning. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 263–272. [find](https://scholar.google.com/scholar?q=Yashoteja+Prabhu+and+Manik+Varma%2E+2014%2E+Fastxml%3A+A+fast%2C+accurate+and+stable+tree%2Dclassifier+for+extreme+multi%2Dlabel+learning%2E+In+Proceedings+of+the+20th+ACM+SIGKDD+international+conference+on+Knowled)
39. Stephen Robertson, Hugo Zaragoza, et al. 2009. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends® in Information Retrieval, 3(4):333–389. [find](https://scholar.google.com/scholar?q=Stephen+Robertson%2C+Hugo+Zaragoza%2C+et+al%2E+2009%2E+The+probabilistic+relevance+framework%3A+Bm25+and+beyond%2E+Foundations+and+Trends%C2%AE+in+Information+Retrieval%2C+3%284%29%3A333%E2%80%93389%2E)
40. Andrea Salfinger, Luca Zaccagna, Francesca Incitti, Gianluca De Nardi, Lorenzo Dal Fabbro, and Lauro Snidaro. 2025. LA2I2F at SemEval-2025 task 5: Reasoning in embedding space – fusing analogical and ontology-based reasoning for document subject tagging. In Proceedings of the 19th International Work… [find](https://scholar.google.com/scholar?q=Andrea+Salfinger%2C+Luca+Zaccagna%2C+Francesca+Incitti%2C+Gianluca+De+Nardi%2C+Lorenzo+Dal+Fabbro%2C+and+Lauro+Snidaro%2E+2025%2E+LA2I2F+at+SemEval%2D2025+task+5%3A+Reasoning+in+embedding+space+%E2%80%93+fusing+analogical+and+)
41. Gauri Salokhe, Irene Onyancha, James Weinheimer, Barbara Richards, Fynvola Le Hunte Ward, and Johannes Keizer. 2023. Agris 2.0: A more flexible, multilingual bibliographic platform. Food and Agriculture Organization of the United Nations (FAO), Knowledge Exchange and Capacity Building Division. Acce… [find](https://scholar.google.com/scholar?q=Gauri+Salokhe%2C+Irene+Onyancha%2C+James+Weinheimer%2C+Barbara+Richards%2C+Fynvola+Le+Hunte+Ward%2C+and+Johannes+Keizer%2E+2023%2E+Agris+2%2E0%3A+A+more+flexible%2C+multilingual+bibliographic+platform%2E+Food+and+Agricultu)
42. Hinrich Schütze, Christopher D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval, volume 39. Cambridge University Press Cambridge. [find](https://scholar.google.com/scholar?q=Hinrich+Sch%C3%BCtze%2C+Christopher+D+Manning%2C+and+Prabhakar+Raghavan%2E+2008%2E+Introduction+to+information+retrieval%2C+volume+39%2E+Cambridge+University+Press+Cambridge%2E)
43. Sumit Singh, Pankaj Goyal, and Uma Tiwary. 2025. silp_nlp at semeval-2025 task 5: Subject recommendation with sentence transformer. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2455–2460. [find](https://scholar.google.com/scholar?q=Sumit+Singh%2C+Pankaj+Goyal%2C+and+Uma+Tiwary%2E+2025%2E+silp%5Fnlp+at+semeval%2D2025+task+5%3A+Subject+recommendation+with+sentence+transformer%2E+In+Proceedings+of+the+19th+International+Workshop+on+Semantic+Evalua)
44. Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. Mpnet: Masked and permuted pre-training for language understanding. Advances in neural information processing systems, 33:16857–16867. [find](https://scholar.google.com/scholar?q=Kaitao+Song%2C+Xu+Tan%2C+Tao+Qin%2C+Jianfeng+Lu%2C+and+Tie%2DYan+Liu%2E+2020%2E+Mpnet%3A+Masked+and+permuted+pre%2Dtraining+for+language+understanding%2E+Advances+in+neural+information+processing+systems%2C+33%3A16857%E2%80%9316867%2E) [our card](https://md.research.elamur.ai/free/en/papers/song-2020-mpnet-masked-permuted-pre-training/)
45. Osma Suominen. 2019. Annif: Diy automated subject indexing using multiple algorithms. LIBER Quarterly: The Journal of the Association of European Research Libraries, 29(1):1–25. [find](https://scholar.google.com/scholar?q=Osma+Suominen%2E+2019%2E+Annif%3A+Diy+automated+subject+indexing+using+multiple+algorithms%2E+LIBER+Quarterly%3A+The+Journal+of+the+Association+of+European+Research+Libraries%2C+29%281%29%3A1%E2%80%9325%2E)
46. Osma Suominen, Juho Inkinen, and Mona Lehtinen. 2025. Annif at the GermEval-2025 LLMs4Subjects task: Traditional XMTC augmented by efficient LLMs. In Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025): Workshops, pages 447–454, Hannover, Germany. HsH Applied Academics. [find](https://scholar.google.com/scholar?q=Osma+Suominen%2C+Juho+Inkinen%2C+and+Mona+Lehtinen%2E+2025%2E+Annif+at+the+GermEval%2D2025+LLMs4Subjects+task%3A+Traditional+XMTC+augmented+by+efficient+LLMs%2E+In+Proceedings+of+the+21st+Conference+on+Natural+Lang)
47. Osma Suominen, Juho Inkinen, Tuomo Virolainen, Moritz Fürneisen, Bruno P. Kinoshita, Sara Veldhoen, Mats Sjöberg, Philipp Zumstein, Robin Neatherway, and Mona Lehtinen. 2023. Annif. [find](https://scholar.google.com/scholar?q=Osma+Suominen%2C+Juho+Inkinen%2C+Tuomo+Virolainen%2C+Moritz+F%C3%BCrneisen%2C+Bruno+P%2E+Kinoshita%2C+Sara+Veldhoen%2C+Mats+Sj%C3%B6berg%2C+Philipp+Zumstein%2C+Robin+Neatherway%2C+and+Mona+Lehtinen%2E+2023%2E+Annif%2E)
48. Yukihiro Tagami. 2017. Annexml: Approximate nearest neighbor search for extreme multi-label classification. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pages 455–464. [find](https://scholar.google.com/scholar?q=Yukihiro+Tagami%2E+2017%2E+Annexml%3A+Approximate+nearest+neighbor+search+for+extreme+multi%2Dlabel+classification%2E+In+Proceedings+of+the+23rd+ACM+SIGKDD+international+conference+on+knowledge+discovery+and+da)
49. T.T. Tanimoto. 1958. An Elementary Mathematical Theory of Classification and Prediction. International Business Machines Corporation. [find](https://scholar.google.com/scholar?q=T%2ET%2E+Tanimoto%2E+1958%2E+An+Elementary+Mathematical+Theory+of+Classification+and+Prediction%2E+International+Business+Machines+Corporation%2E)
50. Hadi Bayrami Asl Tekanlou, Jafar Razmara, Mahsa Sanaei, Mostafa Rahgouy, and Hamed Babaei Giglou. 2025. Homa at semeval-2025 task 5: Aligning librarian records with ontoaligner for subject tagging. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2400–24… [find](https://scholar.google.com/scholar?q=Hadi+Bayrami+Asl+Tekanlou%2C+Jafar+Razmara%2C+Mahsa+Sanaei%2C+Mostafa+Rahgouy%2C+and+Hamed+Babaei+Giglou%2E+2025%2E+Homa+at+semeval%2D2025+task+5%3A+Aligning+librarian+records+with+ontoaligner+for+subject+tagging%2E+In)
51. Xia Tian, Yang Xin, Wu Jing, Xiu Heng, Zhang Xin, Li Yu, Gao Tong, Tan Xi, Hu Dong, Chen Tao, et al. 2025a. Ruc team at semeval-2025 task 5: Fast automated subject indexing: A method based on similar records matching and related subject ranking. In Proceedings of the 19th International Workshop on S… [find](https://scholar.google.com/scholar?q=Xia+Tian%2C+Yang+Xin%2C+Wu+Jing%2C+Xiu+Heng%2C+Zhang+Xin%2C+Li+Yu%2C+Gao+Tong%2C+Tan+Xi%2C+Hu+Dong%2C+Chen+Tao%2C+et+al%2E+2025a%2E+Ruc+team+at+semeval%2D2025+task+5%3A+Fast+automated+subject+indexing%3A+A+method+based+on+similar+)
52. Yicen Tian, Erchen Yu, Yanan Wang, Dailin Li, Jiaqi Yao, Hongfei Lin, Linlin Zong, and Bo Xu. 2025b. Dutir831 at semeval-2025 task 5: A multi-stage llm approach to gnd subject assignment for tibkat records. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), page… [find](https://scholar.google.com/scholar?q=Yicen+Tian%2C+Erchen+Yu%2C+Yanan+Wang%2C+Dailin+Li%2C+Jiaqi+Yao%2C+Hongfei+Lin%2C+Linlin+Zong%2C+and+Bo+Xu%2E+2025b%2E+Dutir831+at+semeval%2D2025+task+5%3A+A+multi%2Dstage+llm+approach+to+gnd+subject+assignment+for+tibkat+re)
53. George Tsatsaronis, Georgios Balikas, Prodromos Malakasiotis, Ioannis Partalas, Matthias Zschunke, Michael R Alvers, Dirk Weissenborn, Anastasia Krithara, Sergios Petridis, Dimitris Polychronopoulos, Yannis Almirantis, John Pavlopoulos, Nicolas Baskiotis, Patrick Gallinari, Thierry Artiéres, Axel-Cy… [find](https://scholar.google.com/scholar?q=George+Tsatsaronis%2C+Georgios+Balikas%2C+Prodromos+Malakasiotis%2C+Ioannis+Partalas%2C+Matthias+Zschunke%2C+Michael+R+Alvers%2C+Dirk+Weissenborn%2C+Anastasia+Krithara%2C+Sergios+Petridis%2C+Dimitris+Polychronopoulos%2C+)
54. Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, et al. 2025. Embeddinggemma: Powerful and lightweight text representations. arXiv preprint arXiv:2509.20354. — [arXiv:2509.20354](https://arxiv.org/abs/2509.20354) [find](https://scholar.google.com/scholar?q=Henrique+Schechter+Vera%2C+Sahil+Dua%2C+Biao+Zhang%2C+Daniel+Salz%2C+Ryan+Mullins%2C+Sindhu+Raghuram+Panyam%2C+Sara+Smoot%2C+Iftekhar+Naim%2C+Joe+Zou%2C+Feiyang+Chen%2C+et+al%2E+2025%2E+Embeddinggemma%3A+Powerful+and+lightweig)
55. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024. Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672. [find](https://scholar.google.com/scholar?q=Liang+Wang%2C+Nan+Yang%2C+Xiaolong+Huang%2C+Linjun+Yang%2C+Rangan+Majumder%2C+and+Furu+Wei%2E+2024%2E+Multilingual+e5+text+embeddings%3A+A+technical+report%2E+arXiv+preprint+arXiv%3A2402%2E05672%2E) [our card](https://md.research.elamur.ai/free/en/papers/wang-2024-multilingual-e5-text-embeddings-technical/)
56. Ian EH Yen, Xiangru Huang, Wei Dai, Pradeep Ravikumar, Inderjit Dhillon, and Eric Xing. 2017. Ppdsparse: A parallel primal-dual sparse method for extreme classification. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 545–553. [find](https://scholar.google.com/scholar?q=Ian+EH+Yen%2C+Xiangru+Huang%2C+Wei+Dai%2C+Pradeep+Ravikumar%2C+Inderjit+Dhillon%2C+and+Eric+Xing%2E+2017%2E+Ppdsparse%3A+A+parallel+primal%2Ddual+sparse+method+for+extreme+classification%2E+In+Proceedings+of+the+23rd+ACM)
57. Ian En-Hsu Yen, Xiangru Huang, Pradeep Ravikumar, Kai Zhong, and Inderjit Dhillon. 2016. Pd-sparse: A primal and dual sparse approach to extreme multiclass and multilabel classification. [find](https://scholar.google.com/scholar?q=Ian+En%2DHsu+Yen%2C+Xiangru+Huang%2C+Pradeep+Ravikumar%2C+Kai+Zhong%2C+and+Inderjit+Dhillon%2E+2016%2E+Pd%2Dsparse%3A+A+primal+and+dual+sparse+approach+to+extreme+multiclass+and+multilabel+classification%2E)
58. In International conference on machine learning, pages 3069–3077. PMLR. [find](https://scholar.google.com/scholar?q=In+International+conference+on+machine+learning%2C+pages+3069%E2%80%933077%2E+PMLR%2E)
59. Ronghui You, Zihan Zhang, Ziye Wang, Suyang Dai, Hiroshi Mamitsuka, and Shanfeng Zhu. 2019. Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. Advances in neural information processing systems, 32. [find](https://scholar.google.com/scholar?q=Ronghui+You%2C+Zihan+Zhang%2C+Ziye+Wang%2C+Suyang+Dai%2C+Hiroshi+Mamitsuka%2C+and+Shanfeng+Zhu%2E+2019%2E+Attentionxml%3A+Label+tree%2Dbased+attention%2Daware+deep+model+for+high%2Dperformance+extreme+multi%2Dlabel+text+clas)
60. Hsiang-Fu Yu, Kai Zhong, Jiong Zhang, Wei-Cheng Chang, and Inderjit S Dhillon. 2022. Pecos: Prediction for enormous and correlated output spaces. Journal of Machine Learning Research, 23(98):1–32. [find](https://scholar.google.com/scholar?q=Hsiang%2DFu+Yu%2C+Kai+Zhong%2C+Jiong+Zhang%2C+Wei%2DCheng+Chang%2C+and+Inderjit+S+Dhillon%2E+2022%2E+Pecos%3A+Prediction+for+enormous+and+correlated+output+spaces%2E+Journal+of+Machine+Learning+Research%2C+23%2898%29%3A1%E2%80%9332%2E)
61. Jiong Zhang, Wei-Cheng Chang, Hsiang-Fu Yu, and Inderjit Dhillon. 2021. Fast multi-resolution transformer fine-tuning for extreme multi-label text classification. Advances in Neural Information Processing Systems, 34:7267–7280. [find](https://scholar.google.com/scholar?q=Jiong+Zhang%2C+Wei%2DCheng+Chang%2C+Hsiang%2DFu+Yu%2C+and+Inderjit+Dhillon%2E+2021%2E+Fast+multi%2Dresolution+transformer+fine%2Dtuning+for+extreme+multi%2Dlabel+text+classification%2E+Advances+in+Neural+Information+Proces)
62. Ruohong Zhang, Yau-Shian Wang, Yiming Yang, Donghan Yu, Tom Vu, and Likun Lei. 2023. Long-tailed extreme multi-label text classification by the retrieval of generated pseudo label descriptions. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1092–1106. [find](https://scholar.google.com/scholar?q=Ruohong+Zhang%2C+Yau%2DShian+Wang%2C+Yiming+Yang%2C+Donghan+Yu%2C+Tom+Vu%2C+and+Likun+Lei%2E+2023%2E+Long%2Dtailed+extreme+multi%2Dlabel+text+classification+by+the+retrieval+of+generated+pseudo+label+descriptions%2E+In+Fin)