---
title: "Named Person Coreference in English News — Agarwal 2018"
description: "The authors propose interpretable NPC metrics instead. 31 references, cited by 1 paper here."
authors: ["Oshin Agarwal", "Sanjay Subramanian", "Ani Nenkova", "Dan Roth"]
year: 2018
venue: "arXiv:1810.11476"
source: "https://arxiv.org/abs/1810.11476"
doi: "10.48550/arxiv.1810.11476"
arxiv: "1810.11476"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/agarwal-2018-named-person-coreference-english-news/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/agarwal-2018-named-person-coreference-english-news/)

[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/6/) / Named Person Coreference in English News

# Named Person Coreference in English News

**Authors:** [Oshin Agarwal](https://md.research.elamur.ai/free/en/authors/oshin-agarwal/), [Sanjay Subramanian](https://md.research.elamur.ai/free/en/authors/sanjay-subramanian/), [Ani Nenkova](https://md.research.elamur.ai/free/en/authors/ani-nenkova/) and [Dan Roth](https://md.research.elamur.ai/free/en/authors/dan-roth/) · **Year:** 2018 · **Venue:** arXiv:1810.11476 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1810.11476) · [PDF](https://arxiv.org/pdf/1810.11476) · [DOI 10.48550/arxiv.1810.11476](https://doi.org/10.48550/arxiv.1810.11476) · [arXiv 1810.11476](https://arxiv.org/abs/1810.11476) · [OpenAlex](https://openalex.org/W2898209642)

**Citations:** 2 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/agarwal-2018-named-person-coreference-english-news/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
The paper looks at a narrow slice of coreference called Named Person Coreference (NPC). The task is to find every mention of a person who is named somewhere in a document, whether the mention is the name itself, a pronoun or a descriptive noun phrase. Using OntoNotes with gold NER labels, the authors show that people are mentioned often and mostly not by name.

They argue that the usual coreference scores (MUC, B3, CEAF, LEA) suit this goal poorly, for two reasons:
- They hardly penalise a system that misses whole person chains.
- They give credit to pronoun clusters that never connect to the correct name.

The authors propose interpretable NPC metrics instead. These count missing chains and report an entity-level F1 that depends on linking to the right name, split by mention type.

They also build NER-DE, a simple rule-based system. It starts from NER names, merges them by name similarity, and attaches pronouns with basic heuristics. NER-DE beats CoreNLP and AllenNLP on the NPC metrics and roughly matches them on standard scores. The approach does not carry over to ORG or GPE entities.

## Key points
- OntoNotes statistics (nw, bn, mz):
  - Only about 45% of person mentions are names.
  - 68% of named people are mentioned more than once.
  - People make up about 15% of clusters but about 25% of mentions that need coreference.
- 86% of person clusters contain at least one named mention.
- About 88% of animate third-person singular pronouns (he, his, she, her…) belong to a chain with a named person.
- Comparison of NER-DE with AllenNLP on persons:

  | System | Chains missed | NPC F1 | Standard average F1 |
  |---|---|---|---|
  | NER-DE | 12.5% | 0.685 | 0.67 |
  | AllenNLP | 31.87% | 0.563 | 0.71 |

- The source of mentions matters for NER-DE:
  - Mentions built from a dependency parse worked better than CoreNLP or CogComp mentions.
  - Gold mentions raised NPC F1 to 0.789.
- For ORG and GPE, the neural systems find about as many chains as the rule-based variant and resolve them better. The NER-driven shortcut only pays off for persons.

## Interesting ideas
- Score coreference by whether each chain reaches the correct name, and report missing entities and per-mention-type F1 (names, pronouns, nominals) separately, so that errors become visible instead of averaged away.
- Build chains outward from names: open one chain per recognised name, merge chains by name similarity, then attach each pronoun to the nearest suitable earlier name. This gives a transparent baseline whose every decision can be traced.
- Define a mention span from the dependency tree: take the subtree headed by the name's last word, cut at a following "and", and absorb a preceding noun with its dependents.
- Test metrics on small hand-built scenarios (e.g. pronouns clustered correctly but with no name) to expose what a score rewards wrongly.
- Run the same pipeline with gold mentions to find the ceiling set by mention detection, and check each entity type separately before trusting a heuristic.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): coreference in prag could be evaluated by whether pronoun chains end in the right named entity, with failures broken down by mention type.
- **I2** (frames): an explainable name-anchored resolver for persons in prag, where each pronoun link has a stated reason (nearest compatible name).
- **I3** (tree): derive entity spans directly from UD subtrees rather than from a separate chunker, keeping mention boundaries consistent with the parse.
- **I4** (learn): add such synthetic "wrong but high-scoring" outputs as negative controls when validating Mova's own evaluation metrics.
- **I5** (world): before relying on a rule for entity tracking, measure it per entity type (person vs organisation vs place) and against gold spans to see where losses come from.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 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

🧭 Topics (2): [English](https://md.research.elamur.ai/free/en/topics/english/) · 1,373 works · [🔗 Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · 550 works

## Cite

Cite as: Oshin Agarwal, Sanjay Subramanian, Ani Nenkova and Dan Roth. 2018. Named Person Coreference in English News. arXiv:1810.11476.

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

```bibtex
@misc{agarwal2018named,
  title = {{Named Person Coreference in English News}},
  author = {Oshin Agarwal, Sanjay Subramanian, Ani Nenkova and Dan Roth},
  year = {2018},
  doi = {10.48550/arxiv.1810.11476},
  eprint = {1810.11476},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1810.11476}
}
```

- [← previous INAOE-UPV at SemEval-2018 Task 3: An Ensemble Approach for Irony Detection in Twitter](https://md.research.elamur.ai/free/en/papers/farias-2018-inaoe-upv-semeval-2018-task/)
- [next → The head the construct: Construct state nominals as a novel window to syntactic movement difficulties in hearing impairment](https://md.research.elamur.ai/free/en/papers/friedmann-2018-head-construct-construct-state-nominals/)
- [↑ back to papers of 2018](https://md.research.elamur.ai/free/en/papers/2018/page/6/)

## References

31 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Artiles, J.; Borthwick, A.; Gonzalo, J.; Sekine, S.; and Amigó, E. 2010. Weps-3 evaluation campaign: Overview of the web people search clustering and attribute extraction tasks. In CLEF. [find](https://scholar.google.com/scholar?q=Artiles%2C+J%2E%3B+Borthwick%2C+A%2E%3B+Gonzalo%2C+J%2E%3B+Sekine%2C+S%2E%3B+and+Amigo%CC%81%2C+E%2E+2010%2E+Weps%2D3+evaluation+campaign%3A+Overview+of+the+web+people+search+clustering+and+attribute+extraction+tasks%2E+In+CLEF%2E)
2. Bagga, A., and Baldwin, B. 1998. [Entity-based cross-document coreferencing using the vector space model](https://md.research.elamur.ai/free/en/papers/bagga-1998-entity-based-cross-document-coreferencing/). In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, COLING-ACL ’98, August 10-14, 1998, Université de Montréal, Montréal, Quebec, Canada. Proceedings of the Conference., 79–85.
3. Cardie, C., and Wagstaf, K. 1999. [Noun phrase coreference as clustering](https://md.research.elamur.ai/free/en/papers/cardie-1999-noun-phrase-coreference-as-clustering/). In 1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora.
4. Clark, K., and Manning, C. D. 2015. [Entity-centric coreference resolution with model stacking](https://md.research.elamur.ai/free/en/papers/clark-2015-entity-centric-coreference-resolution-model/). In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL 2015, July 26-31, 2015, Beijing, China, Volume 1: Long Papers, 1405–1415.
5. Clark, K., and Manning, C. D. 2016. [Deep reinforcement learning for mention-ranking coreference models](https://md.research.elamur.ai/free/en/papers/clark-2016-deep-reinforcement-learning-mention-ranking/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, 2256–2262.
6. De Marneffe, M.-C.; Recasens, M.; and Potts, C. 2015. Modeling the lifespan of discourse entities with application to coreference resolution. J. Artif. Int. Res. 52(1):445–475. [↗](https://doi.org/10.1613/jair.4565)
7. Durrett, G., and Klein, D. 2014. [A joint model for entity analysis: Coreference, typing, and linking](https://md.research.elamur.ai/free/en/papers/durrett-2014-joint-model-entity-analysis-coreference/). TACL 2:477–490. [↗](https://doi.org/10.1162/tacl_a_00197)
8. Finkel, J. R.; Grenager, T.; and Manning, C. D. 2005. [Incorporating non-local information into information extraction systems by gibbs sampling](https://md.research.elamur.ai/free/en/papers/finkel-2005-incorporating-non-local-information-into/). In ACL 2005, 43rd Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 25-30 June 2005, University of Michigan, USA, 363– 370.
9. Han, X., and Sun, L. 2011. A generative entity-mention model for linking entities with knowledge base. In The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, 19-24 June, 2011, Portland, Oregon, USA, 945–954. [find](https://scholar.google.com/scholar?q=Han%2C+X%2E%2C+and+Sun%2C+L%2E+2011%2E+A+generative+entity%2Dmention+model+for+linking+entities+with+knowledge+base%2E+In+The+49th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%3A+Human+Language+Techn)
10. Honnibal, M., and Johnson, M. 2015. [An improved non-monotonic transition system for dependency parsing](https://md.research.elamur.ai/free/en/papers/honnibal-2015-improved-non-monotonic-transition-system/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 1373–1378. Lisbon, Portugal: Association for Computational Linguistics.
11. Ji, H., and Grishman, R. 2011. Knowledge base population: Successful approaches and challenges. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1, HLT ’11, 1148–1158. [find](https://scholar.google.com/scholar?q=Ji%2C+H%2E%2C+and+Grishman%2C+R%2E+2011%2E+Knowledge+base+population%3A+Successful+approaches+and+challenges%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%3A+Human+Langua)
12. Khashabi, D.; Sammons, M.; Zhou, B.; Redman, T.; Christodoulopoulos, C.; Srikumar, V.; Rizzolo, N.; Ratinov, L.; Luo, G.; Do, Q.; Tsai, C.-T.; Roy, S.; Mayhew, S.; Feng, Z.; Wieting, J.; Yu, X.; Song, Y.; Gupta, S.; Upadhyay, S.; Arivazhagan, N.; Ning, Q.; Ling, S.; and Roth, D. 2018. Cogcompnlp: Your swiss army knife for nlp. In 11th Language Resources and Evaluation Conference. [find](https://scholar.google.com/scholar?q=Khashabi%2C+D%2E%3B+Sammons%2C+M%2E%3B+Zhou%2C+B%2E%3B+Redman%2C+T%2E%3B+Christodoulopoulos%2C+C%2E%3B+Srikumar%2C+V%2E%3B+Rizzolo%2C+N%2E%3B+Ratinov%2C+L%2E%3B+Luo%2C+G%2E%3B+Do%2C+Q%2E%3B+Tsai%2C+C%2E%2DT%2E%3B+Roy%2C+S%2E%3B+Mayhew%2C+S%2E%3B+Feng%2C+Z%2E%3B+Wieting%2C+J%2E%3B+Yu%2C+X%2E%3B+Song%2C)
13. Lee, K.; He, L.; Lewis, M.; and Zettlemoyer, L. 2017. [End-to-end neural coreference resolution](https://md.research.elamur.ai/free/en/papers/lee-2017-end-end-neural-coreference-resolution/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, 188–197.
14. Luo, X. 2005. [On coreference resolution performance metrics](https://md.research.elamur.ai/free/en/papers/luo-2005-coreference-resolution-performance-metrics/). In HLT/EMNLP 2005, Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, 6-8 October 2005, Vancouver, British Columbia, Canada, 25–32.
15. Mann, G. S. 2002. Fine-grained proper noun ontologies for question answering. In Proceedings of the 2002 workshop on Building and using semantic networks-Volume 11, 1–7. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mann%2C+G%2E+S%2E+2002%2E+Fine%2Dgrained+proper+noun+ontologies+for+question+answering%2E+In+Proceedings+of+the+2002+workshop+on+Building+and+using+semantic+networks%2DVolume+11%2C+1%E2%80%937%2E+Association+for+Computational+)
16. Mihalcea, R., and Csomai, A. 2007. Wikify!: Linking documents to encyclopedic knowledge. In Proceedings of the Sixteenth ACM Conference on Conference on Information and Knowledge Management, CIKM ’07, 233–242. [find](https://scholar.google.com/scholar?q=Mihalcea%2C+R%2E%2C+and+Csomai%2C+A%2E+2007%2E+Wikify%21%3A+Linking+documents+to+encyclopedic+knowledge%2E+In+Proceedings+of+the+Sixteenth+ACM+Conference+on+Conference+on+Information+and+Knowledge+Management%2C+CIKM+%E2%80%9907%2C)
17. Moosavi, N. S., and Strube, M. 2016. [Which coreference evaluation metric do you trust? a proposal for a link-based entity aware metric](https://md.research.elamur.ai/free/en/papers/moosavi-2016-which-coreference-evaluation-metric-do/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, 632–642.
18. Pan, X.; Cassidy, T.; Hermjakob, U.; Ji, H.; and Knight, K. 2015. Unsupervised entity linking with abstract meaning representation. In NAACL HLT 2015, The 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Denver, Colorado, USA, May 31 - June 5, 2015, 1130–1139. [find](https://scholar.google.com/scholar?q=Pan%2C+X%2E%3B+Cassidy%2C+T%2E%3B+Hermjakob%2C+U%2E%3B+Ji%2C+H%2E%3B+and+Knight%2C+K%2E+2015%2E+Unsupervised+entity+linking+with+abstract+meaning+representation%2E+In+NAACL+HLT+2015%2C+The+2015+Conference+of+the+North+American+Chapter)
19. Pradhan, S. S.; Hovy, E.; Marcus, M.; Palmer, M.; Ramshaw, L.; and Weischedel, R. 2007. Ontonotes: A unified relational semantic representation. International Journal of Semantic Computing 1(04):405–419. [↗](https://doi.org/10.1142/s1793351x07000251)
20. Pradhan, S.; Luo, X.; Recasens, M.; Hovy, E.; Ng, V.; and Strube, M. 2014. [Scoring coreference partitions of predicted mentions: A reference implementation](https://md.research.elamur.ai/free/en/papers/pradhan-2014-scoring-coreference-partitions-predicted-mentions/). In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 30–35. Baltimore, Maryland: Association for Computational Linguistics.
21. Radhakrishnan, P.; Talukdar, P.; and Varma, V. 2018. Elden: Improved entity linking using densified knowledge graphs. In NAACL-HLT. [find](https://scholar.google.com/scholar?q=Radhakrishnan%2C+P%2E%3B+Talukdar%2C+P%2E%3B+and+Varma%2C+V%2E+2018%2E+Elden%3A+Improved+entity+linking+using+densified+knowledge+graphs%2E+In+NAACL%2DHLT%2E)
22. Raghunathan, K.; Lee, H.; Rangarajan, S.; Chambers, N.; Surdeanu, M.; Jurafsky, D.; and Manning, C. D. 2010. [A multi-pass sieve for coreference resolution](https://md.research.elamur.ai/free/en/papers/raghunathan-2010-multi-pass-sieve-coreference-resolution/). In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, EMNLP 2010, 9-11 October 2010, MIT Stata Center, Massachusetts, USA, A meeting of SIGDAT, a Special Interest Group of the ACL, 492–501.
23. Ratinov, L., and Roth, D. 2009. [Design challenges and misconceptions in named entity recognition](https://md.research.elamur.ai/free/en/papers/ratinov-2009-design-challenges-misconceptions-named-entity/). In CoNLL.
24. Stoyanov, V.; Gilbert, N.; Cardie, C.; and Riloff, E. 2009. [Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art](https://md.research.elamur.ai/free/en/papers/stoyanov-2009-conundrums-noun-phrase-coreference-resolution/). In ACL 2009, Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP, 2-7 August 2009, Singapore, 656–664.
25. Tuggener, D. 2014. [Coreference resolution evaluation for higher level applications](https://md.research.elamur.ai/free/en/papers/tuggener-2014-coreference-resolution-evaluation-higher-level/). In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers, 231–235.
26. Vilain, M.; Burger, J.; Aberdeen, J.; Connolly, D.; and Hirschman, L. 1995. [A model-theoretic coreference scoring scheme](https://md.research.elamur.ai/free/en/papers/vilain-1995-model-theoretic-coreference-scoring-scheme/). In Proceedings of the 6th Conference on Message Understanding, MUC6 ’95, 45–52.
27. Wacholder, N.; Ravin, Y.; and Choi, M. 1997. Disambiguation of proper names in text. In Proceedings of the Fifth Conference on Applied Natural Language Processing, ANLC ’97, 202–208. [find](https://scholar.google.com/scholar?q=Wacholder%2C+N%2E%3B+Ravin%2C+Y%2E%3B+and+Choi%2C+M%2E+1997%2E+Disambiguation+of+proper+names+in+text%2E+In+Proceedings+of+the+Fifth+Conference+on+Applied+Natural+Language+Processing%2C+ANLC+%E2%80%9997%2C+202%E2%80%93208%2E)
28. Weerkamp, W.; Berendsen, R.; Kovachev, B.; Meij, E.; Balog, K.; and de Rijke, M. 2011. People searching for people: analysis of a people search engine log. In Proceeding of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SI-GIR 2011, Beijing, China, July 25-29, 2011, 45–54. [find](https://scholar.google.com/scholar?q=Weerkamp%2C+W%2E%3B+Berendsen%2C+R%2E%3B+Kovachev%2C+B%2E%3B+Meij%2C+E%2E%3B+Balog%2C+K%2E%3B+and+de+Rijke%2C+M%2E+2011%2E+People+searching+for+people%3A+analysis+of+a+people+search+engine+log%2E+In+Proceeding+of+the+34th+International+ACM+)
29. West, R.; Gabrilovich, E.; Murphy, K.; Sun, S.; Gupta, R.; and Lin, D. 2014. Knowledge base completion via search-based question answering. In Proceedings of the 23rd international conference on World wide web, 515–526. ACM. [find](https://scholar.google.com/scholar?q=West%2C+R%2E%3B+Gabrilovich%2C+E%2E%3B+Murphy%2C+K%2E%3B+Sun%2C+S%2E%3B+Gupta%2C+R%2E%3B+and+Lin%2C+D%2E+2014%2E+Knowledge+base+completion+via+search%2Dbased+question+answering%2E+In+Proceedings+of+the+23rd+international+conference+on+World)
30. Wick, M.; Culotta, A.; Rohanimanesh, K.; and McCallum, A. 2009. An entity based model for coreference resolution. In Proceedings of the 2009 SIAM International Conference on Data Mining, 365–376. SIAM. [find](https://scholar.google.com/scholar?q=Wick%2C+M%2E%3B+Culotta%2C+A%2E%3B+Rohanimanesh%2C+K%2E%3B+and+McCallum%2C+A%2E+2009%2E+An+entity+based+model+for+coreference+resolution%2E+In+Proceedings+of+the+2009+SIAM+International+Conference+on+Data+Mining%2C+365%E2%80%93376%2E+SIAM)
31. Zhou, L.; Ticrea, M.; and Hovy, E. 2005. Multi-document biography summarization. arXiv preprint cs/0501078. [find](https://scholar.google.com/scholar?q=Zhou%2C+L%2E%3B+Ticrea%2C+M%2E%3B+and+Hovy%2C+E%2E+2005%2E+Multi%2Ddocument+biography+summarization%2E+arXiv+preprint+cs%2F0501078%2E)

*Updated 24 October 2026*