---
title: "Robust Method of Pronoun Resolution Using — Nasukawa 1994"
description: "The paper tackles pronoun antecedent selection in English without hand-built world knowledge, which is costly to acquire and hard to scale."
authors: ["Tetsuya Nasukawa"]
year: 1994
venue: "COLING 1994 Volume 2: The 15th International Conference on Computational Linguistics"
source: "https://aclanthology.org/C94-2189/"
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/papers/nasukawa-1994-robust-method-pronoun-resolution-full/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/nasukawa-1994-robust-method-pronoun-resolution-full/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [1994](https://md.research.elamur.ai/free/papers/1994/) / Robust Method of Pronoun Resolution Using Full-Text Information

# Robust Method of Pronoun Resolution Using Full-Text Information

**Authors:** Tetsuya Nasukawa · **Year:** 1994 · **Venue:** COLING 1994 Volume 2: The 15th International Conference on 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/C94-2189/) · [PDF](https://aclanthology.org/C94-2189.pdf) · [OpenAlex](https://openalex.org/W2042348482)

**Citations:** 34 citations (openalex-snapshot · 2026-10-14) · [8](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper tackles pronoun antecedent selection in English without hand-built world knowledge, which is costly to acquire and hard to scale. The author argues that a coherent document can stand in for such knowledge, since its own sentences show which words combine and which entities are topical. Candidate noun phrases are collected from the current and preceding sentences until two sentences have contributed candidates. Candidates that break number or gender agreement are removed, as are those that cannot be coreferent for syntactic reasons. The remaining candidates are then ranked by three surface cues. The first is the candidate's syntactic position, with subjects favoured. The second is how often its lemma recurs in earlier text, including headings marked by SGML tags. The third is whether an identical modifier–modifiee collocation appears elsewhere in the same document. The method was built into the Shalt2 English-to-Japanese machine translation system and tested on computer manuals, where it resolved 93.8% of pronouns correctly. Its significance is that it reaches knowledge-level accuracy using only light, robust processing of the text itself.

## Key points
- Evaluation covered 112 pronouns in computer manuals, with 105 resolved correctly (93.8%). Candidate lists averaged 4.1 noun phrases.
- In 28 cases the antecedent was inherited from an identical pronoun among the candidates. The other 84 cases were decided by the three preference factors.
- Each factor was also tested alone on those 84 cases:
  - Syntactic position alone was correct about 82% of the time (69 cases).
  - Repetition frequency alone was correct 60.7% of the time (51 cases).
- Matching collocations appeared in only 22 of the 84 cases (26.2%), but they never favoured a wrong candidate. In half of those cases, they overrode a misleading positional or repetition cue.
- The only external resource was an on-line synonym dictionary, used in 7 of the 37 collocation matches (18.9%). Most supporting collocations were found close to the pronoun, both before and after 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: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/)

Topics: [Coreference resolution](https://md.research.elamur.ai/free/topics/coreference-resolution/)

## Cited by

Cited by

8 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 7 not yet.

- [Multilingual Robust Anaphora Resolution](https://md.research.elamur.ai/free/papers/mitkov-1998-multilingual-robust-anaphora-resolution/)

## Cite

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

```bibtex
@inproceedings{nasukawa1994robust,
  title = {{Robust Method of Pronoun Resolution Using Full-Text Information}},
  author = {Nasukawa, Tetsuya},
  booktitle = {COLING 1994 Volume 2: The 15th International Conference on Computational Linguistics},
  year = {1994},
  doi = {10.3115/991250.991340},
  url = {https://doi.org/10.3115/991250.991340}
}
```

- [← previous Research methods and system designs in machine translation: a ten-year review, 1984-1994](https://md.research.elamur.ai/free/papers/hutchins-1994-research-methods-system-designs-machine/)
- [next → Simplified English grammar and style correction in an MT framework: The LRE SECC Project](https://md.research.elamur.ai/free/papers/adriaens-1994-simplified-english-grammar-style-correction/)
- [↑ back to papers of 1994](https://md.research.elamur.ai/free/papers/1994/)

## 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. Brennan, S. E., M. W. Friedman, and C. J. Pollard (1987). A Centering Approach to Pronomls. /:n Proceedings of A CL-8Z [find](https://scholar.google.com/scholar?q=Brennan%2C+S%2E+E%2E%2C+M%2E+W%2E+Friedman%2C+and+C%2E+J%2E+Pollard+%281987%29%2E+A+Centering+Approach+to+Pronomls%2E+%2F%3An+Proceedings+of+A+CL%2D8Z)
2. Carbonell, J. G., and l.I.. D. Brown (1(,)88). Anaphora Resolution: A Multi-Strategy At)proach. in Proceedings of COLING-88. [find](https://scholar.google.com/scholar?q=Carbonell%2C+J%2E+G%2E%2C+and+l%2EI%2E%2E+D%2E+Brown+%281%28%2C%2988%29%2E+Anaphora+Resolution%3A+A+Multi%2DStrategy+At%29proach%2E+in+Proceedings+of+COLING%2D88%2E)
3. Char,dak, E. (1973)..lack and Janet in Search of a Theory of Knowledge. /n Proceedings of IJCAI-72. [find](https://scholar.google.com/scholar?q=Char%2Cdak%2C+E%2E+%281973%29%2E%2Elack+and+Janet+in+Search+of+a+Theory+of+Knowledge%2E+%2Fn+Proceedings+of+IJCAI%2D72%2E)
4. Gale, W. A., K. W. Church, a.ltd D. Yarowsky (1992). One Sense Per l)iscourse. /n Proceedings of the 4th DARPA 5'pecch and Natural Language Workshop [find](https://scholar.google.com/scholar?q=Gale%2C+W%2E+A%2E%2C+K%2E+W%2E+Church%2C+a%2Eltd+D%2E+Yarowsky+%281992%29%2E+One+Sense+Per+l%29iscourse%2E+%2Fn+Proceedings+of+the+4th+DARPA+5%27pecch+and+Natural+Language+Workshop)
5. Hindle, D., ~md M. Rooth (1993). Strnctural Ambiguity and Lexieal Relations. Computational Linguistics, Vol. 19, No. 1. [find](https://scholar.google.com/scholar?q=Hindle%2C+D%2E%2C+%7Emd+M%2E+Rooth+%281993%29%2E+Strnctural+Ambiguity+and+Lexieal+Relations%2E+Computational+Linguistics%2C+Vol%2E+19%2C+No%2E+1%2E)
6. Ilobbs, J. R. (1978). Resolving Pronoun l/,eferenees. Lingua, 4~' [find](https://scholar.google.com/scholar?q=Ilobbs%2C+J%2E+R%2E+%281978%29%2E+Resolving+Pronoun+l%2F%2Ceferenees%2E+Lingua%2C+4%7E%27)
7. Jensen, K., and J.-I,. Binot (1987). Disambiguating Prel)ositionaJ Phrase Attach-. ments by Using ()n-Line Dietioimry 1)eiinitions. Computational Linguistics, Vol. 13, No. 2- 4. [find](https://scholar.google.com/scholar?q=Jensen%2C+K%2E%2C+and+J%2E%2DI%2C%2E+Binot+%281987%29%2E+Disambiguating+Prel%29ositionaJ+Phrase+Attach%2D%2E+ments+by+Using+%28%29n%2DLine+Dietioimry+1%29eiinitions%2E+Computational+Linguistics%2C+Vol%2E+13%2C+No%2E+2%2D+4%2E)
8. Lapi)in , S., and M. McCord (1990). Anaphora ll~esolution in Sh)t Grammar. Computational Linguistics, Vol. 16, No. 4. [find](https://scholar.google.com/scholar?q=Lapi%29in+%2C+S%2E%2C+and+M%2E+McCord+%281990%29%2E+Anaphora+ll%7Eesolution+in+Sh%29t+Grammar%2E+Computational+Linguistics%2C+Vol%2E+16%2C+No%2E+4%2E)
9. Kameyama, M., R. Passonneau, and M. I)oesio (1993). Temporal Centering. In Proceedings of A CL- 93. [find](https://scholar.google.com/scholar?q=Kameyama%2C+M%2E%2C+R%2E+Passonneau%2C+and+M%2E+I%29oesio+%281993%29%2E+Temporal+Centering%2E+In+Proceedings+of+A+CL%2D+93%2E)
10. Nagao, K. (1990). Del)endency Am alyzer: A Knowle(lge-ba.sed A1)proaeh to Structural Disambiguation. [n Procecding.s of COLING-90. [find](https://scholar.google.com/scholar?q=Nagao%2C+K%2E+%281990%29%2E+Del%29endency+Am+alyzer%3A+A+Knowle%28lge%2Dba%2Esed+A1%29proaeh+to+Structural+Disambiguation%2E+%5Bn+Procecding%2Es+of+COLING%2D90%2E)
11. iasukawa, T. (1993). l)iscourse Constraint in Computer Manuals. In Proceedings of TM[-93. [find](https://scholar.google.com/scholar?q=iasukawa%2C+T%2E+%281993%29%2E+l%29iscourse+Constraint+in+Computer+Manuals%2E+In+Proceedings+of+TM%5B%2D93%2E)
12. Rich, E.A. and S. Lul)erFoy (1988). An Architeeturc for AnaI)ttora Resolution. In Proceedings of ANLP-88. [find](https://scholar.google.com/scholar?q=Rich%2C+E%2EA%2E+and+S%2E+Lul%29erFoy+%281988%29%2E+An+Architeeturc+for+AnaI%29ttora+Resolution%2E+In+Proceedings+of+ANLP%2D88%2E)
13. Sidner, C. L. (1983). Focusing in the Coinprehension of Definite Anaphora. In Computational Models of Discourse, M. Brady and R. Bcrwick, cds., Cambridge, Mass.: MIT Press. ['['~keda, 1992] Ta.keda, K., N. Uramoto, T. Nw sukawa, and T. Tsutsmni (1992). Shalt2 - a Syimuetric Machine Translation Syste… [find](https://scholar.google.com/scholar?q=Sidner%2C+C%2E+L%2E+%281983%29%2E+Focusing+in+the+Coinprehension+of+Definite+Anaphora%2E+In+Computational+Models+of+Discourse%2C+M%2E+Brady+and+R%2E+Bcrwick%2C+cds%2E%2C+Cambridge%2C+Mass%2E%3A+MIT+Press%2E+%5B%27%5B%27%7Ekeda%2C+1992%5D+Ta%2Ekeda%2C+K)
14. Uramoto, N. (J991). Lexical and Structural Disambiguation Lrsing all Example-Base./n Proceedings of the 2nd Japan-Australia Joint Symposium on Natural Language Processing. [find](https://scholar.google.com/scholar?q=Uramoto%2C+N%2E+%28J991%29%2E+Lexical+and+Structural+Disambiguation+Lrsing+all+Example%2DBase%2E%2Fn+Proceedings+of+the+2nd+Japan%2DAustralia+Joint+Symposium+on+Natural+Language+Processing%2E)
15. Walker, M. (1989). Evaluating Discourse Processing Algorithms. In Proceedings of A CL-89. [1] "IBM SAA bnagePlus Object Distribution Manager MVS/ESA High-Speed Capture Subsystem Guide Version 2 Release 1.1," IBM Cor-(1991) 1, [2] "IBM Application System/400 New User's Guide Version 2," IBM Corp. (19… [find](https://scholar.google.com/scholar?q=Walker%2C+M%2E+%281989%29%2E+Evaluating+Discourse+Processing+Algorithms%2E+In+Proceedings+of+A+CL%2D89%2E+%5B1%5D+%22IBM+SAA+bnagePlus+Object+Distribution+Manager+MVS%2FESA+High%2DSpeed+Capture+Subsystem+Guide+Version+2+Releas)