---
title: "The Acquisition and Use of Context-Dependent Grammars for"
description: "The authors propose a Context-Dependent Grammar (CDG). 99% accuracy. 25 references, cited by 3 papers here."
authors: ["Robert F. Simmons", "Yeong-Ho Yu"]
year: 1992
venue: "Computational Linguistics"
source: "https://aclanthology.org/J92-4001/"
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/simmons-1992-acquisition-use-context-dependent-grammars/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/simmons-1992-acquisition-use-context-dependent-grammars/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1992](https://md.research.elamur.ai/free/en/papers/1992/) / The Acquisition and Use of Context-Dependent Grammars for English

# The Acquisition and Use of Context-Dependent Grammars for English

**Authors:** [Robert F. Simmons](https://md.research.elamur.ai/free/en/authors/robert-f-simmons/) and [Yeong-Ho Yu](https://md.research.elamur.ai/free/en/authors/yeong-ho-yu/) · **Year:** 1992 · **Venue:** [Computational Linguistics](https://md.research.elamur.ai/free/en/venues/cl/) ([Computational Linguistics 1992](https://md.research.elamur.ai/free/en/venues/cl/1992/)) · **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/J92-4001/) · [PDF](https://aclanthology.org/J92-4001.pdf) · [OpenAlex](https://openalex.org/W1916540122)

**Citations:** 31 citations (OpenAlex, 2026-10-14) · 3 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Simmons and Yu tackle the difficulty of building broad, unambiguous sentence grammars for English. Hand-written augmented context-free grammars are large, hard to maintain and prone to ambiguity. The authors propose a Context-Dependent Grammar (CDG). Each rule pairs a fixed window of parser state with an action: the top five stack symbols plus the next five input symbols, mapped to either a shift or a labelled reduction. A deterministic, single-path shift/reduce parser applies these rules, combining at most two stack elements per reduction. Rules come from interactive sessions in which a linguist demonstrates the correct step for each successive constituent. The grammar sits in a hash table with a selection formula, replacing an earlier back-propagation network that became too costly to train. On 345 sentences, mostly newswire and 10–60 words long, phrase-structure and case analyses reached 99% accuracy. The work suggests that context-based rule grammars are computationally and conceptually manageable for large text subsets.

## Key points
- 16,275 taught example constituents compressed to 3,843 rules, and the compressed grammar parsed just as well.
- Extrapolation suggests about 25,000 example rules would give near-complete phrase-structure coverage of AP Wire text.
- An earlier neural version with 2,000 rules took ten days to train on a Symbolics Lisp Machine. Training cost grew faster than the square of the example count, so the authors moved to hash-table storage.
- The rule left side is a 10-symbol window (5 stack + 5 input, with blanks for padding). The right side is S (shift) or a reduce with a label, such as (R pp).
- The same machinery produces case analyses. Reduce actions attach relations such as AGT, OBJ, MOD, DET, AUX and NMOD between the top stack items.

## Interesting ideas
- A fixed window over the parser stack and lookahead is enough context to choose deterministically between shift and a labelled reduce; shrinking it to two stack items and one input item collapses the system into a binary CFG.
- The grammar is acquired by having a teacher confirm or correct each successive parse step, and every step is stored as a reusable example.
- When a learned model becomes too expensive to retrain, a hash table of exact contexts plus a similarity-based selection formula can serve as a cheap replacement.
- Role labels are assigned inside the reduce action itself, so syntax and shallow case structure come out of one pass.
- Plotting coverage against the number of taught examples lets the authors estimate how much annotation full coverage would need.

## For Mova

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

- **I1** (tree): Each decision of the perceptron parser could log its stack/buffer window as the human-readable reason, giving an explainable trace of every attachment.
- **I2** (learn): LLM-teacher or human corrections to silver parses could be saved as window→action entries, forming self-induced repair rules that are easy to audit.
- **I3** (tree): A lookup table of frequent contexts could sit next to gparse as a fast, transparent fallback, or act as a disagreement check against the neural parser.
- **I4** (frames): Reductions that also emit VerbNet-style roles (agent, object, modifier) could feed who-did-what-to-whom frames directly from parser actions.
- **I5** (learn): Tracking how new rules or examples taper off per added text would help estimate how much silver data a new genre, such as fables or word problems, needs.

*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/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,263 works · [📐 Syntax & grammar formalisms](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) · 214 works

## Cite

Cite as: Robert F. Simmons and Yeong-Ho Yu. 1992. The Acquisition and Use of Context-Dependent Grammars for English. Computational Linguistics.

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

```bibtex
@article{simmons1992acquisition,
  title = {{The Acquisition and Use of Context-Dependent Grammars for English}},
  author = {Robert F. Simmons and Yeong-Ho Yu},
  journal = {Computational Linguistics},
  year = {1992},
  url = {https://aclanthology.org/J92-4001/}
}
```

- [← previous Shake-and-Bake Translation](https://md.research.elamur.ai/free/en/papers/whitelock-1992-shake-bake-translation/)
- [next → Approximating an Interlingua in a Principled Way](https://md.research.elamur.ai/free/en/papers/hovy-1992-approximating-interlingua-principled-way/)
- [↑ back to papers of 1992](https://md.research.elamur.ai/free/en/papers/1992/)

## References

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

1. Alterman, Richard (1985). "A dictionary based on concept coherence," Artificial Intelligence, 25, 153-186. [↗](https://doi.org/10.1016/0004-3702(85)90002-5)
2. Allen, James (1987). Natural Language Understanding. Benjamin Cummings. [find](https://scholar.google.com/scholar?q=Allen%2C+James+%281987%29%2E+Natural+Language+Understanding%2E+Benjamin+Cummings%2E)
3. Allen, Robert (1987). "Several studies on natural language and back propagation." In Proceedings, International Conference on Neural Networks. San Diego. [find](https://scholar.google.com/scholar?q=Allen%2C+Robert+%281987%29%2E+%22Several+studies+on+natural+language+and+back+propagation%2E%22+In+Proceedings%2C+International+Conference+on+Neural+Networks%2E+San+Diego%2E)
4. Berwick, Robert C. (1985). The Acquisition of Syntactic Knowledge, Vol. 2, 335-341. MIT Press. [find](https://scholar.google.com/scholar?q=Berwick%2C+Robert+C%2E+%281985%29%2E+The+Acquisition+of+Syntactic+Knowledge%2C+Vol%2E+2%2C+335%2D341%2E+MIT+Press%2E)
5. Chomsky, Noam (1957). Syntactic Structures. Mouton. [find](https://scholar.google.com/scholar?q=Chomsky%2C+Noam+%281957%29%2E+Syntactic+Structures%2E+Mouton%2E)
6. Cook, Walter (1989). Case Grammar Theory. Georgetown University Press. [find](https://scholar.google.com/scholar?q=Cook%2C+Walter+%281989%29%2E+Case+Grammar+Theory%2E+Georgetown+University+Press%2E)
7. Gazdar, Gerald (1988). "Applicability of indexed grammars to natural languages." In Linguistic Theory and Computer Applications, edited by P. Whitelock, et al., Academic Press, 37--67. [↗](https://doi.org/10.1007/978-94-009-1337-0_3)
8. Gazdar, Gerald, and Mellish, Chris (1989). Natural Language Processing in LISP. Addison-Wesley. [find](https://scholar.google.com/scholar?q=Gazdar%2C+Gerald%2C+and+Mellish%2C+Chris+%281989%29%2E+Natural+Language+Processing+in+LISP%2E+Addison%2DWesley%2E)
9. Gazdar, Gerald; Klein, E.; and Pullum, G.; and Sag, I. (1985). Generalized Phrase Structure Grammar. Harvard University Press. [find](https://scholar.google.com/scholar?q=Gazdar%2C+Gerald%3B+Klein%2C+E%2E%3B+and+Pullum%2C+G%2E%3B+and+Sag%2C+I%2E+%281985%29%2E+Generalized+Phrase+Structure+Grammar%2E+Harvard+University+Press%2E)
10. Semantics and Cognition, MIT Press, Cambridge, Mass., 1983. [find](https://scholar.google.com/scholar?q=Semantics+and+Cognition%2C+MIT+Press%2C+Cambridge%2C+Mass%2E%2C+1983%2E)
11. Joshi, Aravind (1987). "An introduction to tree-adjoining grammars" In Mathematics of Language, edited by A. Manaster-Ramer, 87-114. John Benjamins. [find](https://scholar.google.com/scholar?q=Joshi%2C+Aravind+%281987%29%2E+%22An+introduction+to+tree%2Dadjoining+grammars%22+In+Mathematics+of+Language%2C+edited+by+A%2E+Manaster%2DRamer%2C+87%2D114%2E+John+Benjamins%2E)
12. Leow, Wee-Keng, and Simmons, R. E (1990). "A constraint satisfaction network for case analysis," AI Technical Report AI90-129, Department of Computer Science, University of Texas, Austin. [find](https://scholar.google.com/scholar?q=Leow%2C+Wee%2DKeng%2C+and+Simmons%2C+R%2E+E+%281990%29%2E+%22A+constraint+satisfaction+network+for+case+analysis%2C%22+AI+Technical+Report+AI90%2D129%2C+Department+of+Computer+Science%2C+University+of+Texas%2C+Austin%2E)
13. Marcus, M. P. (1980). A Theory of Syntactic Recognition for Natural Language. MIT Press. [find](https://scholar.google.com/scholar?q=Marcus%2C+M%2E+P%2E+%281980%29%2E+A+Theory+of+Syntactic+Recognition+for+Natural+Language%2E+MIT+Press%2E)
14. McClelland, J. L., and Kawamoto, A. H. (1986). "Mechanisms of sentence processing: Assigning roles to constituents." In Parallel Distributed Processing, Vol. 2, edited by J. L. McClelland and D. E. Rumelhart, MIT Press, 272-326. [find](https://scholar.google.com/scholar?q=McClelland%2C+J%2E+L%2E%2C+and+Kawamoto%2C+A%2E+H%2E+%281986%29%2E+%22Mechanisms+of+sentence+processing%3A+Assigning+roles+to+constituents%2E%22+In+Parallel+Distributed+Processing%2C+Vol%2E+2%2C+edited+by+J%2E+L%2E+McClelland+and+D%2E+E%2E+Ru)
15. Miikkulainen, Risto, and Dyer, M. (1989). "A modular neural network architecture for sequential paraphrasing of script-based stories," Artificial Intelligence Lab., Department of Computer Science, UCLA. [find](https://scholar.google.com/scholar?q=Miikkulainen%2C+Risto%2C+and+Dyer%2C+M%2E+%281989%29%2E+%22A+modular+neural+network+architecture+for+sequential+paraphrasing+of+script%2Dbased+stories%2C%22+Artificial+Intelligence+Lab%2E%2C+Department+of+Computer+Science%2C+UCL)
16. Rim, Hae-Chang (1990). Computing outlines from descriptive texts. Doctoral dissertation, University of Texas, Austin. [find](https://scholar.google.com/scholar?q=Rim%2C+Hae%2DChang+%281990%29%2E+Computing+outlines+from+descriptive+texts%2E+Doctoral+dissertation%2C+University+of+Texas%2C+Austin%2E)
17. Rumelhart, David E.; Hinton, G. E.; and Williams, R. J. (1986). "Learning internal representations by error propagation." In Parallel Distributed Processing, edited by D. E. Rumelhart and J. L. McClelland, MIT Press, 318-362. [↗](https://doi.org/10.21236/ada164453)
18. Schank, Roger C. (1980). "Language and memory," Cognitive Science, 4(3). [↗](https://doi.org/10.1016/s0364-0213(80)80004-8)
19. Seo, Jungyun (1990). Text driven construction of discourse structures for understanding descriptive texts. Doctoral dissertation, University of Texas, Austin. [find](https://scholar.google.com/scholar?q=Seo%2C+Jungyun+%281990%29%2E+Text+driven+construction+of+discourse+structures+for+understanding+descriptive+texts%2E+Doctoral+dissertation%2C+University+of+Texas%2C+Austin%2E)
20. Sejnowski, Xerrence J., and Rosenberg, C. (1988). "NETtalk: A parallel network that learns to read aloud." In Neurocomputing, edited by Anderson and Rosenfeld, MIT Press. [find](https://scholar.google.com/scholar?q=Sejnowski%2C+Xerrence+J%2E%2C+and+Rosenberg%2C+C%2E+%281988%29%2E+%22NETtalk%3A+A+parallel+network+that+learns+to+read+aloud%2E%22+In+Neurocomputing%2C+edited+by+Anderson+and+Rosenfeld%2C+MIT+Press%2E)
21. Shieber, Stuart M. (1986). An Introduction to Unification Based Approaches to Grammar. University of Chicago Press. [find](https://scholar.google.com/scholar?q=Shieber%2C+Stuart+M%2E+%281986%29%2E+An+Introduction+to+Unification+Based+Approaches+to+Grammar%2E+University+of+Chicago+Press%2E)
22. Simmons, Robert F. (1984). Computations from the English. Prentice Hall. [find](https://scholar.google.com/scholar?q=Simmons%2C+Robert+F%2E+%281984%29%2E+Computations+from+the+English%2E+Prentice+Hall%2E)
23. Simmons, Robert F., and Yu, Yeong-Ho (1990). "Training a neural network to be a context sensitive grammar." In Proceedings, 5th Rocky Mountain AI Conference. Las Cruces, NM. [find](https://scholar.google.com/scholar?q=Simmons%2C+Robert+F%2E%2C+and+Yu%2C+Yeong%2DHo+%281990%29%2E+%22Training+a+neural+network+to+be+a+context+sensitive+grammar%2E%22+In+Proceedings%2C+5th+Rocky+Mountain+AI+Conference%2E+Las+Cruces%2C+NM%2E)
24. Tomita, M. (1985). Efficient Parsing for Natural Language. Kluwer Academic Publishers. [↗](https://doi.org/10.1007/978-1-4757-1885-0)
25. Yu, Yeong-Ho, and Simmons, R. E (1990). "Descending epsilon in back-propagation: A technique for better generalization," in press, Proc. Int. Jt. Conf. Neural Networks, San Diego. [find](https://scholar.google.com/scholar?q=Yu%2C+Yeong%2DHo%2C+and+Simmons%2C+R%2E+E+%281990%29%2E+%22Descending+epsilon+in+back%2Dpropagation%3A+A+technique+for+better+generalization%2C%22+in+press%2C+Proc%2E+Int%2E+Jt%2E+Conf%2E+Neural+Networks%2C+San+Diego%2E)

*Updated 1 November 2026*