[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/zeldes-2018-predictive-model-notional-anaphora-english/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [English](https://md.mova.elamur.ai/free/en/docs/papers/en/) / A Predictive Model for Notional Anaphora in English

# A Predictive Model for Notional Anaphora in English

**Authors:** [Amir Zeldes](https://md.mova.elamur.ai/free/en/docs/papers/authors/amir-zeldes/) · **Year:** 2018 · **Venue:** CRAC 2018 (First Workshop on Computational Models of Reference, Anaphora and Coreference) **Link:** [aclanthology.org/W18-0704](https://aclanthology.org/W18-0704/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)

[**6** citations](https://openalex.org/works?filter=cites:W2798290545) openalex · 2026-10-18[**2** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/zeldes-2018-predictive-model-notional-anaphora-english/) of the 140673 papers whose bibliographies we read[Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference](https://aclanthology.org/volumes/W18-07/)[licence](https://creativecommons.org/licenses/by/4.0/)

- [Publisher's page](https://aclanthology.org/W18-0704/)
- [PDF](https://aclanthology.org/W18-0704.pdf)
- [DOI 10.18653/v1/w18-0704](https://doi.org/10.18653/v1/w18-0704)
- [arXiv 1804.07375](https://arxiv.org/abs/1804.07375)
- [OpenAlex](https://openalex.org/W2798290545)

**Authors (1)**

1. [Zeldes, Amir](https://openalex.org/A5089212858) [ORCID](https://orcid.org/0000-0001-8016-6753) · h 17 · 1555 citations · 240 works

Citations and author metrics from openalex (2026-10-18); authors with the same name are not always told apart.

## What it is about

Notional anaphors are plural pronouns whose antecedent is grammatically singular: «the government… they», «CNN… they're on top of everything», «a number of… they», «the person here… they». The paper studies all such cases in OntoNotes (fewer than 4,000 gold examples, with 10% held out) and separates three types: collective or distributive «committee» nouns (the most common), bleached quantity heads (*a number of*, *a majority of*), and singular persons referred to by *they* because gender is unknown or irrelevant, including generics like *nobody… they*. First-person *we* for organisations («the SEC… we») is another frequent case. An Extra Trees ensemble over categorical features (POS and dependency function of anaphor, antecedent and their governors, entity type, genre, article and previous mention of the antecedent) and processing features (distance, length, position) predicts whether a pronoun referring to such a noun will be plural with state-of-the-art accuracy. The most important features are first vs third person, the governor of the anaphor, and genre; notional plurals grow more likely with distance and in spoken genres.

## Ideas

- I1. Relax number agreement in a controlled way in the `pronoun` sieve (`coref/src/sieve.rs`) and in the frame reader's resolver: *they/them/their* may link to a singular antecedent when that antecedent is a collective noun (*government, family, team, crowd, army, enemy, company, people of a town*), a quantity head (*a number/majority/couple/group of*), a singular person noun or indefinite person pronoun (*someone, anyone, nobody, each, the person*), and no strictly agreeing plural candidate is in the window. *We/us/our* may link to an organisation in a speaker's quote. The lists are our own data; print «notional» as the link's evidence. Measure *they/them/their* precision and recall on GUM dev (they: 50.5% precision now).
- I2. Use the paper's processing finding as an ordering rule: prefer a strictly agreeing candidate nearby, and accept a notional one only at a larger distance or when no agreeing one exists; check on GUM dev that the rule does not take links from correct plural antecedents.
- I3. In the tales, «the family», «the people», «the court» followed by *they* are common; count them with `coref explain` on a tale sample before and after I1 to see whether the frame reader's coref role (frame bench) changes.

## For Mova

[35. Reference and coreference](https://md.mova.elamur.ai/free/en/docs/languages/en/35-reference-and-coreference/) §3.5 (split antecedents and plurals), §9; `12-pronouns-determiners-numerals.md` (singular *they*). Code: `coref/src/sieve.rs` and `coref/src/mention.rs` (collective and quantity lists), `prag/src/frames.rs` (`Ctx` agreement). Measures: per-pronoun precision and recall for *they/them/their* on GUM dev; frame bench coref F1.

Topics: [Coreference resolution](https://md.mova.elamur.ai/free/en/docs/papers/topics/coreference-resolution/)

## Cite

The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/w18-0704](https://doi.org/10.18653/v1/w18-0704) · [arXiv 1804.07375](https://arxiv.org/abs/1804.07375)

```
@inproceedings{zeldes2018predictive,
  title = {{A Predictive Model for Notional Anaphora in English}},
  author = {Zeldes, Amir},
  booktitle = {Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference},
  year = {2018},
  doi = {10.18653/v1/w18-0704},
  eprint = {1804.07375},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/w18-0704}
}
```

- [← previous Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories](https://md.mova.elamur.ai/free/en/docs/papers/zarrie-2019-know-what-you-don-t/)
- [next → The DISRPT 2019 Shared Task on Elementary Discourse Unit Segmentation and Connective Detection](https://md.mova.elamur.ai/free/en/docs/papers/zeldes-2019-disrpt-2019-shared-task-elementary/)
- [↑ back to English](https://md.mova.elamur.ai/free/en/docs/papers/en/)

## References

15 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Henri Annala. 2008. Changes in Subject-Verb Agreement with Collective Nouns in British English from the 18th Century to the Present Day. Pro gradu thesis, University of Tampere. [find](https://scholar.google.com/scholar?q=Henri+Annala%2E+2008%2E+Changes+in+Subject%2DVerb+Agreement+with+Collective+Nouns+in+British+English+from+the+18th+Century+to+the+Present+Day%2E+Pro+gradu+thesis%2C+University+of+Tampere%2E)
2. Laura L. Paterson. 2011. The Use and Prescription of Epicene Pronouns: A Corpus-based Approach to Generic he and Singular they in British English. Ph.D. thesis, Loughborough University. [find](https://scholar.google.com/scholar?q=Laura+L%2E+Paterson%2E+2011%2E+The+Use+and+Prescription+of+Epicene+Pronouns%3A+A+Corpus%2Dbased+Approach+to+Generic+he+and+Singular+they+in+British+English%2E+Ph%2ED%2E+thesis%2C+Loughborough+University%2E)
3. BBN Technologies. 2007. Co-reference guidelines for English OntoNotes. version 6.0. Technical report. [find](https://scholar.google.com/scholar?q=BBN+Technologies%2E+2007%2E+Co%2Dreference+guidelines+for+English+OntoNotes%2E+version+6%2E0%2E+Technical+report%2E)
4. Randolph Quirk, Sydney Greenbaum, Geoffrey Leech, and Jan Svartvik. 1985. A Comprehensive Grammar of the English Language. Longman, London. [find](https://scholar.google.com/scholar?q=Randolph+Quirk%2C+Sydney+Greenbaum%2C+Geoffrey+Leech%2C+and+Jan+Svartvik%2E+1985%2E+A+Comprehensive+Grammar+of+the+English+Language%2E+Longman%2C+London%2E)
5. Anne Curzan. 2003. Gender Shifts in the History of English. Studies in English Language. Cambridge University Press, Cambridge. [find](https://scholar.google.com/scholar?q=Anne+Curzan%2E+2003%2E+Gender+Shifts+in+the+History+of+English%2E+Studies+in+English+Language%2E+Cambridge+University+Press%2C+Cambridge%2E)
6. Paul Rayson, Dawn Archer, Scott Piao, and Tony McEnery. 2004. The UCREL semantic analysis system. In Proceedings of the Workshop Beyond Named Entity Recognition: Semantic Labelling for NLP Tasks. Lisbon, Portugal, pages 7–12. [find](https://scholar.google.com/scholar?q=Paul+Rayson%2C+Dawn+Archer%2C+Scott+Piao%2C+and+Tony+McEnery%2E+2004%2E+The+UCREL+semantic+analysis+system%2E+In+Proceedings+of+the+Workshop+Beyond+Named+Entity+Recognition%3A+Semantic+Labelling+for+NLP+Tasks%2E+Lisb)
7. Marcel den Dikken. 2001. “Pluringulars”, pronouns and quirky agreement. The Linguistic Review 18:19–41. [find](https://scholar.google.com/scholar?q=Marcel+den+Dikken%2E+2001%2E+%E2%80%9CPluringulars%E2%80%9D%2C+pronouns+and+quirky+agreement%2E+The+Linguistic+Review+18%3A19%E2%80%9341%2E)
8. Marta Recasens, Marie-Catherine de Marneffe, and Christopher Potts. 2013. The life and death of discourse entities: Identifying singleton mentions. In Proceedings of NAACL 2013. Atlanta, GA, pages 627–633. [find](https://scholar.google.com/scholar?q=Marta+Recasens%2C+Marie%2DCatherine+de+Marneffe%2C+and+Christopher+Potts%2E+2013%2E+The+life+and+death+of+discourse+entities%3A+Identifying+singleton+mentions%2E+In+Proceedings+of+NAACL+2013%2E+Atlanta%2C+GA%2C+pages+627)
9. Marta Recasens, Zhichao Hu, and Olivia Rhinehart. 2016. Sense anaphoric pronouns: Am I one? In Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016), co-located with NAACL 2016. San Diego, CA, pages 1–6. [find](https://scholar.google.com/scholar?q=Marta+Recasens%2C+Zhichao+Hu%2C+and+Olivia+Rhinehart%2E+2016%2E+Sense+anaphoric+pronouns%3A+Am+I+one%3F+In+Proceedings+of+the+Workshop+on+Coreference+Resolution+Beyond+OntoNotes+%28CORBON+2016%29%2C+co%2Dlocated+with+NAA)
10. Wallis Reid. 1991. Verb and Noun Number in English: A Functional Explanation. Longman, London. [find](https://scholar.google.com/scholar?q=Wallis+Reid%2E+1991%2E+Verb+and+Noun+Number+in+English%3A+A+Functional+Explanation%2E+Longman%2C+London%2E)
11. Uli Sauerland. 2003. A new semantics for number. In Proceedings of SALT 13. CLC Publications, Ithaca, NY. [find](https://scholar.google.com/scholar?q=Uli+Sauerland%2E+2003%2E+A+new+semantics+for+number%2E+In+Proceedings+of+SALT+13%2E+CLC+Publications%2C+Ithaca%2C+NY%2E)
12. Nicholas Sobin. 1997. Agreement, default rules, and grammatical viruses. Linguistic Inquiry 28(2):318– 343. [find](https://scholar.google.com/scholar?q=Nicholas+Sobin%2E+1997%2E+Agreement%2C+default+rules%2C+and+grammatical+viruses%2E+Linguistic+Inquiry+28%282%29%3A318%E2%80%93+343%2E)
13. Adrian Staub. 2009. On the interpretation of the number attraction effect: Response time evidence. Journal of Memory and Language 60(2):1–39. [find](https://scholar.google.com/scholar?q=Adrian+Staub%2E+2009%2E+On+the+interpretation+of+the+number+attraction+effect%3A+Response+time+evidence%2E+Journal+of+Memory+and+Language+60%282%29%3A1%E2%80%9339%2E)
14. Matthew W. Wagers, Ellen F. Lau, and Colin Phillips. 2009. Agreement attraction in comprehension: Representations and processes. Journal of Memory and Language 61:206–237. [find](https://scholar.google.com/scholar?q=Matthew+W%2E+Wagers%2C+Ellen+F%2E+Lau%2C+and+Colin+Phillips%2E+2009%2E+Agreement+attraction+in+comprehension%3A+Representations+and+processes%2E+Journal+of+Memory+and+Language+61%3A206%E2%80%93237%2E)
15. Amir Zeldes and Shuo Zhang. 2016. When annotation schemes change rules help: A configurable approach to coreference resolution beyond OntoNotes. In Proceedings of the NAACL2016 Workshop on Coreference Resolution Beyond OntoNotes (CORBON). San Diego, CA, pages 92–101. [find](https://scholar.google.com/scholar?q=Amir+Zeldes+and+Shuo+Zhang%2E+2016%2E+When+annotation+schemes+change+rules+help%3A+A+configurable+approach+to+coreference+resolution+beyond+OntoNotes%2E+In+Proceedings+of+the+NAACL2016+Workshop+on+Coreference)