---
title: "Deep Exhaustive Model for Nested Named Entity Recognition"
description: "Sohrab and Miwa propose a neural exhaustive model that skips token tagging… 77.1% F-score. 25 references, cited by 64 papers here."
authors: ["Mohammad Golam Sohrab", "Makoto Miwa"]
year: 2018
venue: "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/D18-1309/"
doi: "10.18653/v1/d18-1309"
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/sohrab-2018-deep-exhaustive-model-nested-named/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sohrab-2018-deep-exhaustive-model-nested-named/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2018](https://md.research.elamur.ai/free/en/papers/2018/page/2/) / Deep Exhaustive Model for Nested Named Entity Recognition

# Deep Exhaustive Model for Nested Named Entity Recognition

**Authors:** Mohammad Golam Sohrab and [Makoto Miwa](https://md.research.elamur.ai/free/en/authors/makoto-miwa/) · **Year:** 2018 · **Venue:** [Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2018](https://md.research.elamur.ai/free/en/venues/emnlp/2018/)) · **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/D18-1309/) · [PDF](https://aclanthology.org/D18-1309.pdf) · [DOI 10.18653/v1/d18-1309](https://doi.org/10.18653/v1/d18-1309) · [OpenAlex](https://openalex.org/W2892252202)

**Citations:** 235 citations (OpenAlex, 2026-10-14) · [64](https://md.research.elamur.ai/free/en/papers/sohrab-2018-deep-exhaustive-model-nested-named/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Standard named entity recognition treats text as a sequence of token labels. This breaks down when entities are nested, because a single token can belong to several mentions at once. GENIA, for example, has phrases with four levels of nesting. Sohrab and Miwa propose a neural exhaustive model that skips token tagging altogether. It lists every span up to a fixed maximum length and assigns each span an entity type or a non-entity label. A single shared bidirectional LSTM runs over word embeddings and character-level features. Each candidate span is then represented by joining the LSTM states at its two edges with the mean of the states inside it. A ReLU layer and softmax produce the label. Because the LSTM runs only once and spans are classified independently, the approach is efficient and parallelizable. It also uses no POS taggers or other external resources. On the biomedical corpora GENIA (nested) and JNLPBA (flat), it outperformed earlier systems. The work shows that simple span enumeration can handle nesting without CRFs or hand-built features.

## Key points
- **GENIA (nested NER):** 77.1% F-score (P 93.2, R 64.0) with maximum span length 10. This beats Ju et al. (2018) at 74.7, Katiyar and Cardie at 73.8, and Finkel and Manning at 70.3.
- **JNLPBA (flat NER):** 78.4% F-score, compared with 75.8 from the earlier best system (Gridach, 2017).
- **Ablation on the GENIA dev set:**
  - Combining boundary and inside representations gives 78.2 F.
  - Boundary states alone give 68.5.
  - Inside averages alone give 61.2.
  - Character embeddings raise F from 77.1 to 78.2.
- **Span length and coverage:** GENIA mentions average under 4 tokens. A maximum span of 6 already covers 98.9% of mentions, and 10 covers all of them. Longer spans did not hurt accuracy.
- **Setup:**
  - Implemented in Chainer and trained with ADAM.
  - Uses 200-dimensional MEDLINE word embeddings (Chiu et al., 2016).
  - Classification cost per sentence scales as O(lmn): sentence length × maximum span size × number of entity types.

*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

- [Toyota Technological Institute](https://md.research.elamur.ai/free/en/universities/toyota-technological-institute/) — University, Nagoya, Japan · 6 works · 3,321 citations
- [National Institute of Advanced Industrial Science and Technology](https://md.research.elamur.ai/free/en/labs/national-institute-of-advanced-industrial-science-and-technology/) — Research institute, Tsukuba, Japan · 13 works · 2,747 citations
- [Artificial Intelligence Research Center](https://md.research.elamur.ai/free/en/labs/artificial-intelligence-research-center/) — Research institute, Tokyo, Japan · 8 works · 1,556 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 116 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 114 works

🧭 Topics (1): [🏷️ Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · 101 works

## Cite

Cite as: Mohammad Golam Sohrab and Makoto Miwa. 2018. Deep Exhaustive Model for Nested Named Entity Recognition. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{sohrab2018deep,
  title = {{Deep Exhaustive Model for Nested Named Entity Recognition}},
  author = {Mohammad Golam Sohrab and Makoto Miwa},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  year = {2018},
  doi = {10.18653/v1/d18-1309},
  url = {https://doi.org/10.18653/v1/d18-1309}
}
```

- [← previous Learning to Write with Cooperative Discriminators](https://md.research.elamur.ai/free/en/papers/holtzman-2018-learning-write-cooperative-discriminators/)
- [next → Paraphrase Generation with Deep Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/li-2018-paraphrase-generation-deep-reinforcement-learning/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/2/)

## References

25 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Beatrice Alex, Barry Haddow, and Claire Grover. 2007. Recognising Nested Named Entities in Biomedical Text. In Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing, pages 65–72, Stroudsburg, PA, USA. ACL. [find](https://scholar.google.com/scholar?q=Beatrice+Alex%2C+Barry+Haddow%2C+and+Claire+Grover%2E+2007%2E+Recognising+Nested+Named+Entities+in+Biomedical+Text%2E+In+Proceedings+of+the+Workshop+on+BioNLP+2007%3A+Biological%2C+Translational%2C+and+Clinical+Langu)
2. Vinayak Athavale, Shreenivas Bharadwaj, Monik Pamecha, Ameya Prabhu, and Manish Shrivastava. 2016. Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Scarcity. Cornell University Library. [find](https://scholar.google.com/scholar?q=Vinayak+Athavale%2C+Shreenivas+Bharadwaj%2C+Monik+Pamecha%2C+Ameya+Prabhu%2C+and+Manish+Shrivastava%2E+2016%2E+Towards+Deep+Learning+in+Hindi+NER%3A+An+approach+to+tackle+the+Labelled+Data+Scarcity%2E+Cornell+Univers)
3. Billy Chiu, Gamal Crichton, Anna Korhonen, and Sampo Pyysalo. 2016. How to Train good Word Embeddings for Biomedical NLP. In Proceedings of the 15th Workshop on Biomedical Natural Language Processing, pages 166–174. [find](https://scholar.google.com/scholar?q=Billy+Chiu%2C+Gamal+Crichton%2C+Anna+Korhonen%2C+and+Sampo+Pyysalo%2E+2016%2E+How+to+Train+good+Word+Embeddings+for+Biomedical+NLP%2E+In+Proceedings+of+the+15th+Workshop+on+Biomedical+Natural+Language+Processing%2C)
4. N. Collier, H. S. Park, N. Ogata, Y. Tateisi, C. Nobata, T. Ohta, T. Sekimizu, H. Imai, K. Ibushi, and Jun’ichi Tsujii. 1999. The GENIA Project: Corpus-based Knowledge Acquisition and Information Extraction from Genome Research Papers. In Proceedings of EACL, pages 171–172. ACL. [find](https://scholar.google.com/scholar?q=N%2E+Collier%2C+H%2E+S%2E+Park%2C+N%2E+Ogata%2C+Y%2E+Tateisi%2C+C%2E+Nobata%2C+T%2E+Ohta%2C+T%2E+Sekimizu%2C+H%2E+Imai%2C+K%2E+Ibushi%2C+and+Jun%E2%80%99ichi+Tsujii%2E+1999%2E+The+GENIA+Project%3A+Corpus%2Dbased+Knowledge+Acquisition+and+Information+Extr)
5. Xiaocheng Feng, Lifu Huang, Duyu Tang, Heng Ji, Bing Qin, and Ting Liu. 2016. [A Language-Independent Neural Network for Event Detection](https://md.research.elamur.ai/free/en/papers/feng-2016-language-independent-neural-network-event/). In Proceedings of the 54th Annual Meeting of the ACL (Volume 2: Short Papers), pages 66–71, Berlin, Germany.
6. Jenny Rose Finkel and Manning Manning, Christopher D. 2009. [Nested Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/finkel-2009-nested-named-entity-recognition/). In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 141–150, Singapore. ACL.
7. Pavlina Fragkou. 2017. Applying named entity recognition and co-reference resolution for segmenting english texts. Progress in Artificial Intelligence, 6(4):325–346. [find](https://scholar.google.com/scholar?q=Pavlina+Fragkou%2E+2017%2E+Applying+named+entity+recognition+and+co%2Dreference+resolution+for+segmenting+english+texts%2E+Progress+in+Artificial+Intelligence%2C+6%284%29%3A325%E2%80%93346%2E)
8. Mourad Gridach. 2017. Character-level neural network for biomedical named entity recognition. Journal of biomedical informatics, 70:85–91. [find](https://scholar.google.com/scholar?q=Mourad+Gridach%2E+2017%2E+Character%2Dlevel+neural+network+for+biomedical+named+entity+recognition%2E+Journal+of+biomedical+informatics%2C+70%3A85%E2%80%9391%2E)
9. Nitish Gupta, Sameer Singh, and Dan Roth. 2017. [Entity Linking via Joint Encoding of Types, Descriptions, and Context](https://md.research.elamur.ai/free/en/papers/gupta-2017-entity-linking-joint-encoding-types/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2671–2680, Copenhagen, Denmark. ACL.
10. Meizhi Ju, Makoto Miwa, and Sophia Ananiadou. 2018. [A Neural Layered Model for Nested Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/ju-2018-neural-layered-model-nested-named/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1446–1459,…
11. Arzoo Katiyar and Claire Cardie. 2018. [Nested Named Entity Recognition Revisited](https://md.research.elamur.ai/free/en/papers/katiyar-2018-nested-named-entity-recognition-revisited/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 861–871, New Orleans, Louisiana. ACL.
12. Jin-Dong Kim, Tomoko Ohta, Yoshimasa Tsuruoka, Yuka Tateisi, and Nigel Collier. 2004. [Introduction to the Bio-Entity Recognition Task at JNLPBA](https://md.research.elamur.ai/free/en/papers/collier-2004-introduction-bio-entity-recognition-task/). In Proceedings of the international joint workshop on natural language processing in biomedicine and its applications, pages 70–75. ACL.
13. Jin-Dong Kim, Yuka Ohta, Tateisi, and Junichi Tsujii. 2003. GENIA corpus– a semantically annotated corpus for bio-textmining. Bioinformatics, 19(suppl. 1):i180–i182. [find](https://scholar.google.com/scholar?q=Jin%2DDong+Kim%2C+Yuka+Ohta%2C+Tateisi%2C+and+Junichi+Tsujii%2E+2003%2E+GENIA+corpus%E2%80%93+a+semantically+annotated+corpus+for+bio%2Dtextmining%2E+Bioinformatics%2C+19%28suppl%2E+1%29%3Ai180%E2%80%93i182%2E)
14. Diederik Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR. [find](https://scholar.google.com/scholar?q=Diederik+Kingma+and+Jimmy+Ba%2E+2015%2E+Adam%3A+A+Method+for+Stochastic+Optimization%2E+In+ICLR%2E)
15. Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. [Neural Architectures for Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/lample-2016-neural-architectures-named-entity-recognition/). In Proceedings of the 2016 Conference of the North American Chapter of the ACL: Human Language Technologies. ACL, volume 1, pages 260–270, San Diego, C…
16. Wei Lu and Dan Roth. 2015. [Joint Mention Extraction and Classification with Mention Hypergraphs](https://md.research.elamur.ai/free/en/papers/lu-2015-joint-mention-extraction-classification-mention/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 857–867. ACL.
17. Xuezhe Ma and Eduard H. Hovy. 2016. [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://md.research.elamur.ai/free/en/papers/ma-2016-end-end-sequence-labeling-bi/). pages 1064–1074.
18. Makoto Miwa and Mohit Bansal. 2016. [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://md.research.elamur.ai/free/en/papers/miwa-2016-end-end-relation-extraction-lstms/). In Proceedings of the 54th Annual Meeting of the ACL, pages 1105–1116, Berlin, Germany. ACL.
19. Aldrian Obaja Muis and Wei Lu. 2017. Labeling Gaps Between Words: Recognizing Overlapping Mentions with Mention Separators. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2598–2608, Copenhagen, Denmark. ACL. [find](https://scholar.google.com/scholar?q=Aldrian+Obaja+Muis+and+Wei+Lu%2E+2017%2E+Labeling+Gaps+Between+Words%3A+Recognizing+Overlapping+Mentions+with+Mention+Separators%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+Langua)
20. Dan Shen, Jie Zhang, Guodong Zhou, Jian Su, and Chew-Lim Tan. 2003. Effective Adaptation of a Hidden Markov Model-based Named Entity Recognizer for Biomedical Domain. In Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine-Volume 13, pages 49–56, Sapporo, Japan. ACL. [find](https://scholar.google.com/scholar?q=Dan+Shen%2C+Jie+Zhang%2C+Guodong+Zhou%2C+Jian+Su%2C+and+Chew%2DLim+Tan%2E+2003%2E+Effective+Adaptation+of+a+Hidden+Markov+Model%2Dbased+Named+Entity+Recognizer+for+Biomedical+Domain%2E+In+Proceedings+of+the+ACL+2003+wo)
21. Nguyen Truong Son and Nguyen Le Minh. 2017. Nested Named Entity Recognition Using Multilayer Recurrent Neural Networks. In Proceedings of PA-CLING 2017, pages 16–18, Sedona Hotel, Yangon, Myanmar. [find](https://scholar.google.com/scholar?q=Nguyen+Truong+Son+and+Nguyen+Le+Minh%2E+2017%2E+Nested+Named+Entity+Recognition+Using+Multilayer+Recurrent+Neural+Networks%2E+In+Proceedings+of+PA%2DCLING+2017%2C+pages+16%E2%80%9318%2C+Sedona+Hotel%2C+Yangon%2C+Myanmar%2E)
22. M. Stone and R. Arora. 2017. Identifying nominals with no head match co-references using deep learning. CoRR abs/1710.00936. — [arXiv:1710.00936](https://arxiv.org/abs/1710.00936) [find](https://scholar.google.com/scholar?q=M%2E+Stone+and+R%2E+Arora%2E+2017%2E+Identifying+nominals+with+no+head+match+co%2Dreferences+using+deep+learning%2E+CoRR+abs%2F1710%2E00936%2E+%E2%80%94+%5BarXiv%3A1710%2E00936%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1710%2E00936%29)
23. Emma Strubell, Patrick Verga, David Belanger, and Andrew McCallum. 2017. [Fast and Accurate Entity Recognition with Iterated Dilated Convolutions](https://md.research.elamur.ai/free/en/papers/strubell-2017-fast-accurate-entity-recognition-iterated/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2670–2680, Copenhagen, Denmark. ACL.
24. Mingbin Xu, Hui Jiang, and Sedtawut Watcharawit-tayakul. 2017. A Local Detection Approach for Named Entity Recognition and Mention Detection. In Proceedings of the 55th Annual Meeting of the ACL (Volume 1: Long Papers), volume 1, pages 1237–1247. [find](https://scholar.google.com/scholar?q=Mingbin+Xu%2C+Hui+Jiang%2C+and+Sedtawut+Watcharawit%2Dtayakul%2E+2017%2E+A+Local+Detection+Approach+for+Named+Entity+Recognition+and+Mention+Detection%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+ACL+%28Volu)
25. Guodong Zhou, Jie Zhang, Jian Su, Dan Shen, and Chewlim Tan. 2004. Recognizing Names in Biomedical Texts: a Machine Learning Approach. Bioinformatics, 20(7):1178–1190. [find](https://scholar.google.com/scholar?q=Guodong+Zhou%2C+Jie+Zhang%2C+Jian+Su%2C+Dan+Shen%2C+and+Chewlim+Tan%2E+2004%2E+Recognizing+Names+in+Biomedical+Texts%3A+a+Machine+Learning+Approach%2E+Bioinformatics%2C+20%287%29%3A1178%E2%80%931190%2E)

*Updated 24 October 2026*