Paul Smolensky
Biographic Data
| ID | 149378 |
|---|---|
| NAME | Paul Smolensky |
| GIVEN NAMES | Paul |
| FAMILY NAME | Smolensky |
| SIGNATURE | SMOLENSKY P |
| AFFILIATIONS | Johns Hopkins University |
| ORCID | 0000-0003-2420-182X |
| VERIFIED | Yes |
| TOTAL WORKS | 17 |
| TOTAL CITATIONS | 47 |
| AUTHOR COUNT | 17 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 1978 |
| LATEST PUBLICATION YEAR | 2020 |
| H-INDEX | 2 |
Learning a gradient grammar of French liaison
In certain French words, an orthgraphically-final consonant is unpronounced except, in certain environments, when it precedes a vowel. This phenomenon, liaison, shows significant interactions with several other patterns in French (including h-aspiré, schwa deletion, and the presence of other morphemes in the liaison context). We present a learning algorithm that acquires a grammar that accounts for these patterns and their interactions. The learn…
Incremental parsing in a continuous dynamical system: Sentence processing in Gradient Symbolic Computation
Any incremental parser must solve two computational problems: (1) maintaining all interpretations consistent with the words that have been processed so far and (2) excluding all globally-incoherent interpretations. While these problems are well understood, it is not clear how the dynamic, continuous mechanisms that underlie human language processing solve them. We introduce a Gradient Symbolic Computation (GSC) parser, a continuous-state, continu…
How constrained is language mixing in bi- and uni-modal production
Preview this article: How constrained is language mixing in bi- and uni-modal production?, Page 1 of 1 /docserver/preview/fulltext/lab.6.6.13put-1.gif
Learning biases predict a word order universal
Listeners' knowledge of phonological universals: Evidence from nasal clusters
Optimality Theory explains typological markedness implications by proposing that all speakers possess universal constraints penalising marked structures, irrespective of the evidence provided by their language (Prince & Smolensky 2004). The account of phonological perception sketched here entails that markedness constraints reveal their presence by inducing perceptual ‘repairs’ to structures ungrammatical in the hearer's language. As onset cluste…
Optimality Theory: Constraint Interaction in Generative Grammar
Deriving output probabilities in child Mandarin from a Dual-Optimization grammar
Learnability in Optimality Theory
Highlighting the close relationship between linguistic explanation and learnability, Bruce Tesar and Paul Smolensky examine the implications of Optimality Theory (OT) for language learnability. Highlighting the close relationship between linguistic explanation and learnability, Bruce Tesar and Paul Smolensky examine the implications of Optimality Theory (OT) for language learnability. They show how the core principles of OT lead to the learning p…
Learning optimality-theoretic grammars
Learnability in Optimality Theory
In this article we show how Optimality Theory yields a highly general Constraint Demotion principle for grammar learning. The resulting learning procedure specifically exploits the grammatical structure of Optimality Theory, independent of the content of substantive constraints defining any given grammatical module. We decompose the learning problem and present formal results for a central subproblem, deducing the constraint ranking particular to…
On the Proper Treatment of Connectionism
An Optimality-Theoretic Typology of Case and Grammatical Voice Systems
Proceedings of the Nineteenth Annual Meeting of the Berkeley Linguistics Society: General Session and Parasession on Semantic Typology and Semantic Universals (1993)
Unifying Syntactic and Semantic Approaches to Unaccusativity: A Connectionist Approach
Proceedings of the Seventeenth Annual Meeting of the Berkeley Linguistics Society: General Session and Parasession on The Grammar of Event Structure (1991), pp. 156-167
Representation in Connectionist Networks
Connectionist representations are mappings between elements in the problem domain and vectors of activity values. Since cognitive problems do not specify how this representation is to be done, an important part of connectionist cognitive modeling is specifying such a representation. Complex cognitive processing requires representation of complex structured data. This can be done by decomposing structures into roles and fillers, and building up co…
On the proper treatment of connectionism
A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts…
Public Assistance, Female Headship, and Economic Well-Being
Katharine Bradbury, Sheldon Danziger, Eugene Smolensky, Paul Smolensky, Public Assistance, Female Headship, and Economic Well-Being, Journal of Marriage and Family, Vol. 41, No. 3, Family Policy (Aug., 1979), pp. 519-535
Electricity Economics. Essays and Case Studies
Journal Article Electricity Economics. Essays and Case Studies Get access Electricity Economics. Essays and Case Studies. By Ralph Turvey and Dennis Anderson. (London: The Johns Hopkins University Press for The World Bank, 1977. Pp. xvii + 364.)The Marginal Cost and Pricing of Electricity. An Applied Approach. By Charles J . Cicchetti, William J. Gillen and Paul Smolensky. (Cambridge: Ballinger, 1977. Distributed by John Wiley & Sons, London. Pp.…
Learnability in Optimality Theory
In this article we show how Optimality Theory yields a highly general Constraint Demotion principle for grammar learning. The resulting learning procedure specifically exploits the grammatical structure of Optimality Theory, independent of the content of substantive constraints defining any given grammatical module. We decompose the learning problem and present formal results for a central subproblem, deducing the constraint ranking particular to…
Public Assistance, Female Headship, and Economic Well-Being
Katharine Bradbury, Sheldon Danziger, Eugene Smolensky, Paul Smolensky, Public Assistance, Female Headship, and Economic Well-Being, Journal of Marriage and Family, Vol. 41, No. 3, Family Policy (Aug., 1979), pp. 519-535
Deriving output probabilities in child Mandarin from a Dual-Optimization grammar
Learning optimality-theoretic grammars
Electricity Economics. Essays and Case Studies
Journal Article Electricity Economics. Essays and Case Studies Get access Electricity Economics. Essays and Case Studies. By Ralph Turvey and Dennis Anderson. (London: The Johns Hopkins University Press for The World Bank, 1977. Pp. xvii + 364.)The Marginal Cost and Pricing of Electricity. An Applied Approach. By Charles J . Cicchetti, William J. Gillen and Paul Smolensky. (Cambridge: Ballinger, 1977. Distributed by John Wiley & Sons, London. Pp.…
Public Assistance, Female Headship, and Economic Well-Being
Katharine Bradbury, Sheldon Danziger, Eugene Smolensky, Paul Smolensky, Public Assistance, Female Headship, and Economic Well-Being, Journal of Marriage and Family, Vol. 41, No. 3, Family Policy (Aug., 1979), pp. 519-535
On the proper treatment of connectionism
A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts…
Representation in Connectionist Networks
Connectionist representations are mappings between elements in the problem domain and vectors of activity values. Since cognitive problems do not specify how this representation is to be done, an important part of connectionist cognitive modeling is specifying such a representation. Complex cognitive processing requires representation of complex structured data. This can be done by decomposing structures into roles and fillers, and building up co…
Unifying Syntactic and Semantic Approaches to Unaccusativity: A Connectionist Approach
Proceedings of the Seventeenth Annual Meeting of the Berkeley Linguistics Society: General Session and Parasession on The Grammar of Event Structure (1991), pp. 156-167
On the Proper Treatment of Connectionism
An Optimality-Theoretic Typology of Case and Grammatical Voice Systems
Proceedings of the Nineteenth Annual Meeting of the Berkeley Linguistics Society: General Session and Parasession on Semantic Typology and Semantic Universals (1993)
Learning optimality-theoretic grammars
Learnability in Optimality Theory
In this article we show how Optimality Theory yields a highly general Constraint Demotion principle for grammar learning. The resulting learning procedure specifically exploits the grammatical structure of Optimality Theory, independent of the content of substantive constraints defining any given grammatical module. We decompose the learning problem and present formal results for a central subproblem, deducing the constraint ranking particular to…
Learnability in Optimality Theory
Highlighting the close relationship between linguistic explanation and learnability, Bruce Tesar and Paul Smolensky examine the implications of Optimality Theory (OT) for language learnability. Highlighting the close relationship between linguistic explanation and learnability, Bruce Tesar and Paul Smolensky examine the implications of Optimality Theory (OT) for language learnability. They show how the core principles of OT lead to the learning p…
Optimality Theory: Constraint Interaction in Generative Grammar
Deriving output probabilities in child Mandarin from a Dual-Optimization grammar
Listeners' knowledge of phonological universals: Evidence from nasal clusters
Optimality Theory explains typological markedness implications by proposing that all speakers possess universal constraints penalising marked structures, irrespective of the evidence provided by their language (Prince & Smolensky 2004). The account of phonological perception sketched here entails that markedness constraints reveal their presence by inducing perceptual ‘repairs’ to structures ungrammatical in the hearer's language. As onset cluste…
Learning biases predict a word order universal
How constrained is language mixing in bi- and uni-modal production
Preview this article: How constrained is language mixing in bi- and uni-modal production?, Page 1 of 1 /docserver/preview/fulltext/lab.6.6.13put-1.gif
Incremental parsing in a continuous dynamical system: Sentence processing in Gradient Symbolic Computation
Any incremental parser must solve two computational problems: (1) maintaining all interpretations consistent with the words that have been processed so far and (2) excluding all globally-incoherent interpretations. While these problems are well understood, it is not clear how the dynamic, continuous mechanisms that underlie human language processing solve them. We introduce a Gradient Symbolic Computation (GSC) parser, a continuous-state, continu…
Learning a gradient grammar of French liaison
In certain French words, an orthgraphically-final consonant is unpronounced except, in certain environments, when it precedes a vowel. This phenomenon, liaison, shows significant interactions with several other patterns in French (including h-aspiré, schwa deletion, and the presence of other morphemes in the liaison context). We present a learning algorithm that acquires a grammar that accounts for these patterns and their interactions. The learn…
Computer Science (13 works) · Linguistics (10 works) · Psychology (8 works) · Artificial Intelligence (7 works) · Mathematics (7 works) · Natural Language Processing Techniques (7 works) · Philosophy (7 works) · Natural language processing (6 works) · Optimality theory (5 works) · Artificial Intelligence (4 works)