---
title: "Named Entity Recognition using an HMM-based — Zhou 2002"
description: "The paper addresses English named entity recognition: locating and classifying names of persons, organizations and locations, as well as dates, times…"
authors: ["GuoDong Zhou", "Jian Su"]
year: 2002
venue: "Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics"
source: "https://aclanthology.org/P02-1060/"
doi: "10.3115/1073083.1073163"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhou-2002-named-entity-recognition-hmm-based/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhou-2002-named-entity-recognition-hmm-based/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2002](https://md.research.elamur.ai/free/en/papers/2002/) / Named Entity Recognition using an HMM-based Chunk Tagger

# Named Entity Recognition using an HMM-based Chunk Tagger

**Authors:** [GuoDong Zhou](https://md.research.elamur.ai/free/en/authors/guodong-zhou/), [Jian Su](https://md.research.elamur.ai/free/en/authors/jian-su/) · **Year:** 2002 · **Venue:** Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P02-1060/) · [PDF](https://aclanthology.org/P02-1060.pdf) · [DOI 10.3115/1073083.1073163](https://doi.org/10.3115/1073083.1073163) · [OpenAlex](https://openalex.org/W2123512824)

**Citations:** 715 citations (openalex-snapshot · 2026-10-14) · [79](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper addresses English named entity recognition: locating and classifying names of persons, organizations and locations, as well as dates, times, percentages and money amounts. At the time, learning-based systems still lagged handcrafted rule systems by about two points. Zhou and Su adapt their HMM-based chunk tagger, which was the best individual system at CoNLL'2000, by treating each entity as an "NE-Chunk". Unlike the classic HMM in BBN's IdentiFinder, their model factorizes the problem under a mutual information independence assumption. This lets each tag draw on the surrounding context, not just its own word. Each token pairs a word with a composite feature that combines four sources of evidence: surface shape (capitals, digits), semantic classes of trigger words, gazetteer matches, and links to entities already identified elsewhere in the same document. A two-level back-off scheme handles sparse data. On the MUC-6 and MUC-7 NE tasks, the system reaches F-measures of 96.6% and 94.1%. The authors report that these scores beat all published machine-learning and rule-based systems, which suggests that a trainable model can match expert-written rules.

## Key points
- Results: MUC-6 reaches F 96.6 (P 96.3, R 96.9) and MUC-7 reaches F 94.1 (P 93.7, R 94.5). In both cases the MUC dry-run data served for development and the formal test data for testing.
- Training sizes were about 1330 KB for MUC-6 and 708 KB for MUC-7. A learning curve on MUC-7 shows roughly 90% F at 200 KB of training data and a clear drop at 100 KB.
- Feature ablation on MUC-7:
  - f1 (shape features) alone gives 77.6.
  - Adding f2 (triggers) gives 87.4.
  - Adding f4 (document macro context) on top of f1+f2 gives 92.9.
  - All four sub-features give 94.1, so the gazetteer (f3) adds only about 1.2 points.
- Each tag is structured into three parts: a boundary category (0 = whole entity, 1/2/3 = beginning/middle/end), an entity class, and the word feature. Viterbi decoding uses a table of allowed tag transitions to enforce well-formed chunks.
- Sparseness is handled in two back-off stages. The first falls back through progressively smaller windows of features and words. The second falls back through subsets of the four sub-features, always keeping f1.

## Interesting ideas
- **Document-level memory as a feature.** The model marks a token when it matches or abbreviates an entity already recognized in the same document. This exploits consistency within a single text and gave the second-largest gain in the ablation. It would transfer easily to alias-heavy domains such as company or place names in trade data.
- **Trigger words grouped by meaning.** Instead of raw cue words, important context and in-name words are collected semi-automatically from training data and grouped into semantic classes. This was the single largest gain, and it gives a cheap way to inject lexical knowledge into any sequence labeler.
- **Prioritized, mutually exclusive shape classes.** Orthographic and numeric features are checked in a fixed priority order, with a special class for capitalized sentence-initial words. This avoids overlapping features and keeps the sentence-start capitalization ambiguity explicit. Such a scheme is simple to re-implement for another language.
- **Enriched tags plus hard transition constraints.** Folding the word feature into the tag gives finer-grained statistics. A validity table blocks impossible boundary sequences during decoding. Any BIO-style tagger could adopt this to guarantee well-formed spans.
- **Reading the ablation critically.** The authors explain the gazetteer's small contribution by noting that it mainly helps well-known names that appear without helpful context. When building resources, this is a useful reminder to measure what a lexicon adds beyond contextual cues before investing heavily in it.

*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: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/)

## Cited by

Cited by

79 papers of our library cite it (of the 140884 whose bibliographies we read); 1 of them have a page here, 78 not yet.

- [A Survey on Recent Advances in Named Entity Recognition from Deep Learning models](https://md.research.elamur.ai/free/en/papers/yadav-2018-survey-recent-advances-named-entity/)

## Cite

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

```bibtex
@inproceedings{zhou2002named,
  title = {{Named Entity Recognition using an HMM-based Chunk Tagger}},
  author = {Zhou, GuoDong and Su, Jian},
  booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics},
  year = {2002},
  doi = {10.3115/1073083.1073163},
  url = {https://doi.org/10.3115/1073083.1073163}
}
```

- [← previous Kernel Methods for Relation Extraction](https://md.research.elamur.ai/free/en/papers/zelenko-2002-kernel-methods-relation-extraction/)
- [next → From TreeBank to PropBank](https://md.research.elamur.ai/free/en/papers/kingsbury-2002-treebank-propbank/)
- [↑ back to papers of 2002](https://md.research.elamur.ai/free/en/papers/2002/)

## References

27 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. J. Aberdeen, D. Day, L. Hirschman, P. Robinson and M. Vilain. MITRE: Description of the Alembic System Used for MUC-6. MUC-6 . Pages141-155. Columbia, Maryland. 1995. [find](https://scholar.google.com/scholar?q=J%2E+Aberdeen%2C+D%2E+Day%2C+L%2E+Hirschman%2C+P%2E+Robinson+and+M%2E+Vilain%2E+MITRE%3A+Description+of+the+Alembic+System+Used+for+MUC%2D6%2E+MUC%2D6+%2E+Pages141%2D155%2E+Columbia%2C+Maryland%2E+1995%2E)
2. C. Aone, L. Halverson, T. Hampton, M. Ramos-Santacruz. SRA: Description of the IE2 System Used for MUC-7. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=C%2E+Aone%2C+L%2E+Halverson%2C+T%2E+Hampton%2C+M%2E+Ramos%2DSantacruz%2E+SRA%3A+Description+of+the+IE2+System+Used+for+MUC%2D7%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
3. S.W. Bennett, C. Aone and C. Lovell. Learning to Tag Multilingual Texts Through Observation. EMNLP'1996 . Pages109-116. Providence, Rhode Island. 1996. [find](https://scholar.google.com/scholar?q=S%2EW%2E+Bennett%2C+C%2E+Aone+and+C%2E+Lovell%2E+Learning+to+Tag+Multilingual+Texts+Through+Observation%2E+EMNLP%271996+%2E+Pages109%2D116%2E+Providence%2C+Rhode+Island%2E+1996%2E)
4. Daniel M. Bikel, Richard Schwartz and Ralph M. Weischedel. An Algorithm that Learns What's in a Name. Machine Learning (Special Issue on NLP). 1999. [find](https://scholar.google.com/scholar?q=Daniel+M%2E+Bikel%2C+Richard+Schwartz+and+Ralph+M%2E+Weischedel%2E+An+Algorithm+that+Learns+What%27s+in+a+Name%2E+Machine+Learning+%28Special+Issue+on+NLP%29%2E+1999%2E)
5. A. Borthwick, J. Sterling, E. Agichtein, R. Grishman. NYU: Description of the MENE Named Entity System as Used in MUC-7. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=A%2E+Borthwick%2C+J%2E+Sterling%2C+E%2E+Agichtein%2C+R%2E+Grishman%2E+NYU%3A+Description+of+the+MENE+Named+Entity+System+as+Used+in+MUC%2D7%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
6. Andrew Borthwick. A Maximum Entropy Approach to Named Entity Recognition. Ph.D. Thesis. New York University. September, 1999. [find](https://scholar.google.com/scholar?q=Andrew+Borthwick%2E+A+Maximum+Entropy+Approach+to+Named+Entity+Recognition%2E+Ph%2ED%2E+Thesis%2E+New+York+University%2E+September%2C+1999%2E)
7. Eric Brill. Transform-based Error-Driven Learning and Natural Language Processing: A Case Study in Part-of-speech Tagging. Computational Linguistics 21(4). Pages543-565. 1995. [find](https://scholar.google.com/scholar?q=Eric+Brill%2E+Transform%2Dbased+Error%2DDriven+Learning+and+Natural+Language+Processing%3A+A+Case+Study+in+Part%2Dof%2Dspeech+Tagging%2E+Computational+Linguistics+21%284%29%2E+Pages543%2D565%2E+1995%2E)
8. Nancy Chinchor. MUC-6 Named Entity Task Definition (Version 2.1). MUC-6 . Columbia, Maryland. 1995. [find](https://scholar.google.com/scholar?q=Nancy+Chinchor%2E+MUC%2D6+Named+Entity+Task+Definition+%28Version+2%2E1%29%2E+MUC%2D6+%2E+Columbia%2C+Maryland%2E+1995%2E)
9. Nancy Chinchor. Statistical Significance of MUC-6 Results. MUC-6 . Columbia, Maryland. 1995. [find](https://scholar.google.com/scholar?q=Nancy+Chinchor%2E+Statistical+Significance+of+MUC%2D6+Results%2E+MUC%2D6+%2E+Columbia%2C+Maryland%2E+1995%2E)
10. Nancy Chinchor. MUC-7 Named Entity Task Definition (Version 3.5). MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=Nancy+Chinchor%2E+MUC%2D7+Named+Entity+Task+Definition+%28Version+3%2E5%29%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
11. Nancy Chinchor. Statistical Significance of MUC-7 Results. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=Nancy+Chinchor%2E+Statistical+Significance+of+MUC%2D7+Results%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
12. K. Humphreys, R. Gaizauskas, S. Azzam, C. Huyck, B. Mitchell, H. Cunningham, Y. Wilks. Univ. of Sheffield: Description of the LaSIE-II System as Used for MUC-7. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=K%2E+Humphreys%2C+R%2E+Gaizauskas%2C+S%2E+Azzam%2C+C%2E+Huyck%2C+B%2E+Mitchell%2C+H%2E+Cunningham%2C+Y%2E+Wilks%2E+Univ%2E+of+Sheffield%3A+Description+of+the+LaSIE%2DII+System+as+Used+for+MUC%2D7%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
13. G. R. Krupka, K. Hausman. IsoQuest Inc.: Description of the NetOwl TM Extractor System as Used for MUC-7. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=G%2E+R%2E+Krupka%2C+K%2E+Hausman%2E+IsoQuest+Inc%2E%3A+Description+of+the+NetOwl+TM+Extractor+System+as+Used+for+MUC%2D7%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
14. D. McDonald. Internal and External Evidence in the Identification and Semantic Categorization of Proper Names. In B. Boguraev and J. Pustejovsky editors: Corpus Processing for Lexical Acquisition . Pages21-39. MIT Press. Cambridge, MA. 1996. [find](https://scholar.google.com/scholar?q=D%2E+McDonald%2E+Internal+and+External+Evidence+in+the+Identification+and+Semantic+Categorization+of+Proper+Names%2E+In+B%2E+Boguraev+and+J%2E+Pustejovsky+editors%3A+Corpus+Processing+for+Lexical+Acquisition+%2E+Pa)
15. S. Miller, M. Crystal, H. Fox, L. Ramshaw, R. Schwartz, R. Stone, R. Weischedel, and the Annotation Group. BBN: Description of the SIFT System as Used for MUC-7. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=S%2E+Miller%2C+M%2E+Crystal%2C+H%2E+Fox%2C+L%2E+Ramshaw%2C+R%2E+Schwartz%2C+R%2E+Stone%2C+R%2E+Weischedel%2C+and+the+Annotation+Group%2E+BBN%3A+Description+of+the+SIFT+System+as+Used+for+MUC%2D7%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
16. A. Mikheev, C. Grover, M. Moens. Description of the LTG System Used for MUC-7. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=A%2E+Mikheev%2C+C%2E+Grover%2C+M%2E+Moens%2E+Description+of+the+LTG+System+Used+for+MUC%2D7%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
17. A. Mikheev, M. Moens, and C. Grover. Named entity recognition without gazeteers. EACL'1999 . Pages1-8. Bergen, Norway. 1999. [find](https://scholar.google.com/scholar?q=A%2E+Mikheev%2C+M%2E+Moens%2C+and+C%2E+Grover%2E+Named+entity+recognition+without+gazeteers%2E+EACL%271999+%2E+Pages1%2D8%2E+Bergen%2C+Norway%2E+1999%2E)
18. Morgan Kaufmann Publishers, Inc. Proceedings of the Sixth Message Understanding Conference (MUC-6) . Columbia, Maryland. 1995. [find](https://scholar.google.com/scholar?q=Morgan+Kaufmann+Publishers%2C+Inc%2E+Proceedings+of+the+Sixth+Message+Understanding+Conference+%28MUC%2D6%29+%2E+Columbia%2C+Maryland%2E+1995%2E)
19. Morgan Kaufmann Publishers, Inc. Proceedings of the Seventh Message Understanding Conference (MUC-7) . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=Morgan+Kaufmann+Publishers%2C+Inc%2E+Proceedings+of+the+Seventh+Message+Understanding+Conference+%28MUC%2D7%29+%2E+Fairfax%2C+Virginia%2E+1998%2E)
20. L. Rabiner. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition”. IEEE 77( 2). Pages257-285. 1989. [find](https://scholar.google.com/scholar?q=L%2E+Rabiner%2E+A+Tutorial+on+Hidden+Markov+Models+and+Selected+Applications+in+Speech+Recognition%E2%80%9D%2E+IEEE+77%28+2%29%2E+Pages257%2D285%2E+1989%2E)
21. Satoshi Sekine. Description of the Japanese NE System Used for MET-2. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=Satoshi+Sekine%2E+Description+of+the+Japanese+NE+System+Used+for+MET%2D2%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
22. Erik F. Tjong Kim Sang and Sabine Buchholz. Introduction to the CoNLL-2000 Shared Task: Chunking. CoNLL'2000 . Pages127-132. Lisbon, Portugal. 11-14 Sept 2000. [find](https://scholar.google.com/scholar?q=Erik+F%2E+Tjong+Kim+Sang+and+Sabine+Buchholz%2E+Introduction+to+the+CoNLL%2D2000+Shared+Task%3A+Chunking%2E+CoNLL%272000+%2E+Pages127%2D132%2E+Lisbon%2C+Portugal%2E+11%2D14+Sept+2000%2E) [our card](https://md.research.elamur.ai/free/en/papers/sang-2000-introduction-conll-2000-shared-task/)
23. A. J. Viterbi. Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm. IEEE Transactions on Information Theory. IT(13). Pages260-269, April 1967. [find](https://scholar.google.com/scholar?q=A%2E+J%2E+Viterbi%2E+Error+Bounds+for+Convolutional+Codes+and+an+Asymptotically+Optimum+Decoding+Algorithm%2E+IEEE+Transactions+on+Information+Theory%2E+IT%2813%29%2E+Pages260%2D269%2C+April+1967%2E)
24. B. Watson and Tsoi A Chunk. Second Order Hidden Markov Models for Speech Recognition”. Proceeding of 4 th Australian International Conference on Speech Science and Technology . Pages146-151. 1992. [find](https://scholar.google.com/scholar?q=B%2E+Watson+and+Tsoi+A+Chunk%2E+Second+Order+Hidden+Markov+Models+for+Speech+Recognition%E2%80%9D%2E+Proceeding+of+4+th+Australian+International+Conference+on+Speech+Science+and+Technology+%2E+Pages146%2D151%2E+1992%2E)
25. Yu Shihong, Bai Shuanhu and Wu Paul. Description of the Kent Ridge Digital Labs System Used for MUC-7. MUC-7 . Fairfax, Virginia. 1998. [find](https://scholar.google.com/scholar?q=Yu+Shihong%2C+Bai+Shuanhu+and+Wu+Paul%2E+Description+of+the+Kent+Ridge+Digital+Labs+System+Used+for+MUC%2D7%2E+MUC%2D7+%2E+Fairfax%2C+Virginia%2E+1998%2E)
26. Zhou GuoDong, Su Jian and Tey TongGuan. Hybrid Text Chunking. CoNLL'2000 . Pages163-166. Lisbon, Portugal, 11-14 Sept 2000. [find](https://scholar.google.com/scholar?q=Zhou+GuoDong%2C+Su+Jian+and+Tey+TongGuan%2E+Hybrid+Text+Chunking%2E+CoNLL%272000+%2E+Pages163%2D166%2E+Lisbon%2C+Portugal%2C+11%2D14+Sept+2000%2E)
27. Zhou GuoDong and Su Jian, Error-driven HMM-based Chunk Tagger with Context-dependent Lexicon. EMNLP/ VLC'2000 . Hong Kong, 7-8 Oct 2000. [find](https://scholar.google.com/scholar?q=Zhou+GuoDong+and+Su+Jian%2C+Error%2Ddriven+HMM%2Dbased+Chunk+Tagger+with+Context%2Ddependent+Lexicon%2E+EMNLP%2F+VLC%272000+%2E+Hong+Kong%2C+7%2D8+Oct+2000%2E)