---
title: "Toward Treating English Nominals Correctly — Sproat 1987"
description: "The authors argue that stress depends on syntactic level (N⁰ compounds versus higher… 80% accuracy. 14 references, cited by 1 paper here."
authors: ["Richard W. Sproat", "Mark Y. Liberman"]
year: 1987
venue: "25th Annual Meeting of the Association for Computational Linguistics"
source: "https://aclanthology.org/P87-1020/"
doi: "10.3115/981175.981195"
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/sproat-1987-treating-english-nominals-correctly/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sproat-1987-treating-english-nominals-correctly/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1987](https://md.research.elamur.ai/free/en/papers/1987/) / Toward Treating English Nominals Correctly

# Toward Treating English Nominals Correctly

**Authors:** [Richard W. Sproat](https://md.research.elamur.ai/free/en/authors/richard-sproat/) and [Mark Y. Liberman](https://md.research.elamur.ai/free/en/authors/mark-liberman/) · **Year:** 1987 · **Venue:** [25th Annual Meeting of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 1987](https://md.research.elamur.ai/free/en/venues/acl/1987/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/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/P87-1020/) · [PDF](https://aclanthology.org/P87-1020.pdf) · [DOI 10.3115/981175.981195](https://doi.org/10.3115/981175.981195) · [OpenAlex](https://openalex.org/W2146154850)

**Citations:** 8 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/sproat-1987-treating-english-nominals-correctly/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Sproat and Liberman address how a text-to-speech system should place stress in English complex nominals, meaning a head noun that follows at least one open-class modifier (e.g. *dog catcher*, *Madison Avenue*, *City Hall parking lot*). Such nominals are frequent and often phrase-final, so misplacing their main accent noticeably harms synthetic speech. The authors argue that stress depends on syntactic level (N⁰ compounds versus higher X-bar attachments), on meaning relations between the words, and on special constructions such as names. Their program has two parts. For binary nominals it first checks a phrasal lexicon of exceptionally left-stressed items. Otherwise it collects weighted heuristic patterns (measure phrases, location/time/substance modifiers, deverbal heads, *self*, place names, a weak noun-noun default) and lets them vote. For n-ary nominals it recursively combines binary results on a metrical grid and applies the Rhythm Rule. On 200 binary nominals the program reached 80% accuracy, compared with 45% for uniform right stress. The same lexical knowledge also helps bracket complex nominals.

## Key points
- The Brown Corpus contains over 73,000 nominals longer than two words. Focus or contrast shifts the main stress in only a fraction of a percent of phrase-final cases.
- The lexicon lists roughly 7000 left-stressed nominals. The authors stress that being lexicalized neither guarantees nor is required for left stress (*red herring* is listed yet right-stressed; *dog annihilator* is unlisted yet left-stressed).
- In deverbal heads (-ing, -er, other affixes), a left member read as the verb's object tends to get left stress (*dog catcher*). A left member read as its subject tends to get right stress (*woman swimmer*).
- Evaluation on 200 [N N] items from Bell Labs News gave these accuracies:
  - uniform right stress: 45%
  - left stress whenever the item is noun+noun: 66%
  - the full program: 80%
- Of about 40 errors, roughly 30 came from missing knowledge (e.g. chemical terms like *gallium arsenide*) and only about 10 from misanalysis. The authors judge 90–95% to be a reachable target.

## Interesting ideas
- Each heuristic casts a vote weighted by how reliable it is, so a near-certain pattern like [self N] dominates while the vague noun-noun default barely counts; this cleanly combines weak and strong evidence.
- The paper asks what role the modifier plays for a deverbal head (object versus subject of the underlying verb) and treats this as a real semantic decision rather than a surface fact.
- The authors split failures into "insufficient information" and "misanalysis," which shows whether to invest in more knowledge or in better rules.
- The program is compared against two trivial baselines (always right, and left only for noun+noun), which makes the 80% figure meaningful.
- Modifier classes such as measure unit, location, time, and substance determine how the compound behaves, and semantic word classes double as rule triggers.

## For Mova

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

- **I1** (tree): Bracketing of multi-noun compounds could use such weighted, inspectable votes, with each vote logged as an explanation for the chosen attachment.
- **I2** (frames): Nominalizations like *baby sitting* or *student dancing* could be mapped to verb frames, with the left noun assigned a Patient or Agent role.
- **I3** (learn): Evaluation reports could tag every error with this split, directing effort toward lexicon or ontology growth versus repairs to the rules.
- **I4** (learn): Each component evaluation could include such cheap default baselines as negative controls, so that gains are measured against what a naive rule already achieves.
- **I5** (world): WordNet/Wikidata classes for measures, places, and materials could label compound relations (*pint jug* = capacity, *wood floor* = made-of), and these labels could feed both the world model and prosody in generation.

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

## Institutions

- [AT&T](https://md.research.elamur.ai/free/en/companies/at-t/) — Company, Bedminster, United States · 40 works · 75,466 citations

📚 Shelves (6): [🖥️ 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 · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 870 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,263 works

## Cite

Cite as: Richard W. Sproat and Mark Y. Liberman. 1987. Toward Treating English Nominals Correctly. 25th Annual Meeting of the Association for Computational Linguistics.

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

```bibtex
@inproceedings{sproat1987toward,
  title = {{Toward Treating English Nominals Correctly}},
  author = {Richard W. Sproat and Mark Y. Liberman},
  booktitle = {25th Annual Meeting of the Association for Computational Linguistics},
  year = {1987},
  doi = {10.3115/981175.981195},
  url = {https://doi.org/10.3115/981175.981195}
}
```

- [← previous Pattern Recognition Applied to the Acquisition of a Grammatical Classification System From Unrestricted English Text](https://md.research.elamur.ai/free/en/papers/atwell-1987-pattern-recognition-applied-acquisition-grammatical/)
- [next → Machine Translation, Linguistics, and Interlingua](https://md.research.elamur.ai/free/en/papers/sgall-1987-machine-translation-linguistics-interlingua/)
- [↑ back to papers of 1987](https://md.research.elamur.ai/free/en/papers/1987/)

## References

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

1. Bolinger, D. 1972. Accent is Predictable (if you're a mind-reader). Language 48, 633-45. [↗](https://doi.org/10.2307/412039)
2. Chomsky, N. and M. Halle 1968. The Sound Pattern of English. New York: Harper and Row. [find](https://scholar.google.com/scholar?q=Chomsky%2C+N%2E+and+M%2E+Halle+1968%2E+The+Sound+Pattern+of+English%2E+New+York%3A+Harper+and+Row%2E)
3. Finin, T. 1980. The Semantic Interpretation of Compound Nominals. Doctoral dissertation, University of Illinois. [find](https://scholar.google.com/scholar?q=Finin%2C+T%2E+1980%2E+The+Semantic+Interpretation+of+Compound+Nominals%2E+Doctoral+dissertation%2C+University+of+Illinois%2E)
4. Francis, W. N. and Ku~era, H. 1982. Frequency Analysis of English Usage: Lexicon and Grammar. Boston: Houghton Mifflin Company. [find](https://scholar.google.com/scholar?q=Francis%2C+W%2E+N%2E+and+Ku%7Eera%2C+H%2E+1982%2E+Frequency+Analysis+of+English+Usage%3A+Lexicon+and+Grammar%2E+Boston%3A+Houghton+Mifflin+Company%2E)
5. Fudge, E. 1984. English Word-Stress. London and Boston: Allen and Unwin. [find](https://scholar.google.com/scholar?q=Fudge%2C+E%2E+1984%2E+English+Word%2DStress%2E+London+and+Boston%3A+Allen+and+Unwin%2E)
6. Hayes, B. 1980. A Metrical Theory of Stress Rules. Doctoral dissertation, MIT, distributed by Indiana University Linguistics Club. lackendoff, R. X-bar Syntax: A Study of Phrase-Structure. Cambridge and London: MIT Press. [find](https://scholar.google.com/scholar?q=Hayes%2C+B%2E+1980%2E+A+Metrical+Theory+of+Stress+Rules%2E+Doctoral+dissertation%2C+MIT%2C+distributed+by+Indiana+University+Linguistics+Club%2E+lackendoff%2C+R%2E+X%2Dbar+Syntax%3A+A+Study+of+Phrase%2DStructure%2E+Cambridge+a)
7. Lees, R. 1960. The Grammar of English Nominalizations. Bloomington: Indiana University Press. [find](https://scholar.google.com/scholar?q=Lees%2C+R%2E+1960%2E+The+Grammar+of+English+Nominalizations%2E+Bloomington%3A+Indiana+University+Press%2E)
8. Levi, J. 1978. The Syntax and Semantics of Complex Nominals. New York and London: Academic Press. [find](https://scholar.google.com/scholar?q=Levi%2C+J%2E+1978%2E+The+Syntax+and+Semantics+of+Complex+Nominals%2E+New+York+and+London%3A+Academic+Press%2E)
9. Liberman, M. 1975. The Intonational System of English. Doctoral dissertation, MIT, reprinted 1979 by Garland, New York and London. [find](https://scholar.google.com/scholar?q=Liberman%2C+M%2E+1975%2E+The+Intonational+System+of+English%2E+Doctoral+dissertation%2C+MIT%2C+reprinted+1979+by+Garland%2C+New+York+and+London%2E)
10. Liberman, M. and A. Prince 1977. On Stress and Linguistic Rhythm. Linguistic Inquiry 8, 249-336. [find](https://scholar.google.com/scholar?q=Liberman%2C+M%2E+and+A%2E+Prince+1977%2E+On+Stress+and+Linguistic+Rhythm%2E+Linguistic+Inquiry+8%2C+249%2D336%2E)
11. Liberman, M. and R. Sproat 1986. Stress Patterns in English Noun Phrases. Ms., AT&T Bell Labs. 1980. A Theory of Syntactic Recognition for Natural Language. Marcus, M. Cambridge and London: MIT Press. [find](https://scholar.google.com/scholar?q=Liberman%2C+M%2E+and+R%2E+Sproat+1986%2E+Stress+Patterns+in+English+Noun+Phrases%2E+Ms%2E%2C+AT%26T+Bell+Labs%2E+1980%2E+A+Theory+of+Syntactic+Recognition+for+Natural+Language%2E+Marcus%2C+M%2E+Cambridge+and+London%3A+MIT+Press%2E)
12. Prince, A. 1983. Relating to the Grid. Linguistic Inquiry, 14, 19-100. [find](https://scholar.google.com/scholar?q=Prince%2C+A%2E+1983%2E+Relating+to+the+Grid%2E+Linguistic+Inquiry%2C+14%2C+19%2D100%2E)
13. Quirk, R., $. Greenbanm and G. Leech 1972. A Grammar of Contemporary English. London: Longman. [find](https://scholar.google.com/scholar?q=Quirk%2C+R%2E%2C+%24%2E+Greenbanm+and+G%2E+Leech+1972%2E+A+Grammar+of+Contemporary+English%2E+London%3A+Longman%2E)
14. Selkirk, E. 1984. Phonology and Syntax. Cambridge Press. and London: MIT [find](https://scholar.google.com/scholar?q=Selkirk%2C+E%2E+1984%2E+Phonology+and+Syntax%2E+Cambridge+Press%2E+and+London%3A+MIT)

*Updated 1 November 2026*