default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDPaul Smolensky
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c32]Kate McCurdy, Paul Soulos, Paul Smolensky, Roland Fernandez, Jianfeng Gao:
Toward Compositional Behavior in Neural Models: A Survey of Current Views. EMNLP 2024: 9323-9339- [i27]Paul Smolensky, Roland Fernandez, Zhenghao Herbert Zhou, Mattia Opper, Jianfeng Gao:
Mechanisms of Symbol Processing for In-Context Learning in Transformer Networks. CoRR abs/2410.17498 (2024) - 2023
- [j13]R. Thomas McCoy, Paul Smolensky, Tal Linzen, Jianfeng Gao, Asli Celikyilmaz:
How Much Do Language Models Copy From Their Training Data? Evaluating Linguistic Novelty in Text Generation Using RAVEN. Trans. Assoc. Comput. Linguistics 11: 652-670 (2023) - [c31]Paul Soulos, Edward J. Hu, Kate McCurdy, Yunmo Chen, Roland Fernandez, Paul Smolensky, Jianfeng Gao:
Differentiable Tree Operations Promote Compositional Generalization. ICML 2023: 32499-32520 - [i26]Paul Soulos, Edward J. Hu, Kate McCurdy, Yunmo Chen, Roland Fernandez, Paul Smolensky, Jianfeng Gao:
Differentiable Tree Operations Promote Compositional Generalization. CoRR abs/2306.00751 (2023) - [i25]Yuntian Deng, Kiran Prasad, Roland Fernandez, Paul Smolensky, Vishrav Chaudhary, Stuart M. Shieber:
Implicit Chain of Thought Reasoning via Knowledge Distillation. CoRR abs/2311.01460 (2023) - 2022
- [j12]Paul Smolensky
, Richard Thomas McCoy, Roland Fernandez, Matthew Goldrick, Jianfeng Gao:
Neurocompositional Computing: From the Central Paradox of Cognition to a New Generation of AI Systems. AI Mag. 43(3): 308-322 (2022) - [j11]Laurel Brehm, Pyeong Whan Cho, Paul Smolensky, Matthew A. Goldrick:
PIPS: A Parallel Planning Model of Sentence Production. Cogn. Sci. 46(2) (2022) - [i24]Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew Goldrick, Jianfeng Gao:
Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems. CoRR abs/2205.01128 (2022) - [i23]Paul Soulos, Sudha Rao, Caitlin Smith, Eric Rosen, Asli Celikyilmaz, R. Thomas McCoy, Yichen Jiang, Coleman Haley, Roland Fernandez, Hamid Palangi, Jianfeng Gao, Paul Smolensky:
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages. CoRR abs/2208.06061 (2022) - [i22]Najoung Kim, Tal Linzen, Paul Smolensky:
Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models. CoRR abs/2212.10769 (2022) - 2021
- [c30]Richard Thomas McCoy, Jennifer Culbertson, Paul Smolensky, Geraldine Legendre:
Infinite use of finite means? Evaluating the generalization of center embedding learned from an artificial grammar. CogSci 2021 - [c29]Jacob L. Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, Nebojsa Jojic, Paul Smolensky, Jianfeng Gao:
Compositional processing emerges in neural networks solving math problems. CogSci 2021 - [c28]Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao:
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization. NAACL-HLT 2021: 4780-4793 - [i21]Jacob L. Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, Nebojsa Jojic, Paul Smolensky, Jianfeng Gao:
Compositional Processing Emerges in Neural Networks Solving Math Problems. CoRR abs/2105.08961 (2021) - [i20]Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao:
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization. CoRR abs/2106.01317 (2021) - [i19]Matthias Lalisse, Eric Rosen, Paul Smolensky:
Scalable knowledge base completion with superposition memories. CoRR abs/2110.12341 (2021) - [i18]Matthias Lalisse, Paul Smolensky:
Distributed neural encoding of binding to thematic roles. CoRR abs/2110.12342 (2021) - [i17]R. Thomas McCoy, Paul Smolensky, Tal Linzen, Jianfeng Gao, Asli Celikyilmaz:
How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN. CoRR abs/2111.09509 (2021) - 2020
- [c27]Paul Soulos, R. Thomas McCoy, Tal Linzen, Paul Smolensky:
Discovering the Compositional Structure of Vector Representations with Role Learning Networks. BlackboxNLP@EMNLP 2020: 238-254 - [c26]Richard Thomas McCoy, Erin Grant, Paul Smolensky, Tom Griffiths, Tal Linzen:
Universal linguistic inductive biases via meta-learning. CogSci 2020 - [c25]Coleman Haley, Paul Smolensky:
Invertible Tree Embeddings using a Cryptographic Role Embedding Scheme. COLING 2020: 3671-3683 - [c24]Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao:
Mapping natural-language problems to formal-language solutions using structured neural representations. ICML 2020: 1566-1575 - [i16]R. Thomas McCoy, Erin Grant, Paul Smolensky, Thomas L. Griffiths, Tal Linzen:
Universal linguistic inductive biases via meta-learning. CoRR abs/2006.16324 (2020) - [i15]Hassan Akbari, Hamid Palangi, Jianwei Yang, Sudha Rao, Asli Celikyilmaz, Roland Fernandez, Paul Smolensky, Jianfeng Gao, Shih-Fu Chang:
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language. CoRR abs/2011.09530 (2020)
2010 – 2019
- 2019
- [c23]Najoung Kim, Kyle Rawlins, Benjamin Van Durme, Paul Smolensky:
Predicting the Argumenthood of English Prepositional Phrases. AAAI 2019: 6578-6585 - [c22]R. Thomas McCoy, Tal Linzen, Ewan Dunbar, Paul Smolensky:
RNNs implicitly implement tensor-product representations. ICLR (Poster) 2019 - [i14]Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao:
Natural- to formal-language generation using Tensor Product Representations. CoRR abs/1910.02339 (2019) - [i13]Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao:
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving. CoRR abs/1910.06611 (2019) - [i12]Paul Soulos, Tom McCoy, Tal Linzen, Paul Smolensky:
Discovering the Compositional Structure of Vector Representations with Role Learning Networks. CoRR abs/1910.09113 (2019) - [i11]Mehrad Moradshahi, Hamid Palangi, Monica S. Lam, Paul Smolensky, Jianfeng Gao:
HUBERT Untangles BERT to Improve Transfer across NLP Tasks. CoRR abs/1910.12647 (2019) - 2018
- [c21]Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng:
Question-Answering with Grammatically-Interpretable Representations. AAAI 2018: 5350-5357 - [c20]Pyeong Whan Cho, Matthew Goldrick, Richard L. Lewis, Paul Smolensky:
Dynamic encoding of structural uncertainty in gradient symbols. CMCL 2018: 19-28 - [c19]Roland Fernandez, Asli Celikyilmaz, Paul Smolensky, Rishabh Singh:
Learning and Analyzing Vector Encoding of Symbolic Representation. ICLR (Workshop) 2018 - [c18]Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng, Dapeng Oliver Wu:
Tensor Product Generation Networks for Deep NLP Modeling. NAACL-HLT 2018: 1263-1273 - [i10]Paul F. Tupper, Paul Smolensky, Pyeong Whan Cho:
Discrete symbolic optimization and Boltzmann sampling by continuous neural dynamics: Gradient Symbolic Computation. CoRR abs/1801.03562 (2018) - [i9]Roland Fernandez, Asli Celikyilmaz, Rishabh Singh, Paul Smolensky:
Learning and analyzing vector encoding of symbolic representations. CoRR abs/1803.03834 (2018) - [i8]Najoung Kim, Kyle Rawlins, Benjamin Van Durme, Paul Smolensky:
Predicting Argumenthood of English Preposition Phrases. CoRR abs/1809.07889 (2018) - [i7]Shuai Tang, Paul Smolensky, Virginia R. de Sa:
Learning Distributed Representations of Symbolic Structure Using Binding and Unbinding Operations. CoRR abs/1810.12456 (2018) - [i6]Matthias Lalisse, Paul Smolensky:
Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations. CoRR abs/1811.01062 (2018) - [i5]R. Thomas McCoy, Tal Linzen, Ewan Dunbar, Paul Smolensky:
RNNs Implicitly Implement Tensor Product Representations. CoRR abs/1812.08718 (2018) - 2017
- [i4]Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng:
Deep Learning of Grammatically-Interpretable Representations Through Question-Answering. CoRR abs/1705.08432 (2017) - [i3]Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng, Dapeng Oliver Wu:
Tensor Product Generation Networks. CoRR abs/1709.09118 (2017) - [i2]Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng, Dapeng Oliver Wu:
A Neural-Symbolic Approach to Natural Language Tasks. CoRR abs/1710.11475 (2017) - 2016
- [c17]Pyeong Whan Cho, Paul Smolensky:
Bifurcation analysis of a Gradient Symbolic Computation model of incremental processing. CogSci 2016 - [c16]Moontae Lee, Xiaodong He, Wen-tau Yih, Jianfeng Gao, Li Deng, Paul Smolensky:
Reasoning in Vector Space: An Exploratory Study of Question Answering. ICLR (Poster) 2016 - [i1]Paul Smolensky, Moontae Lee, Xiaodong He, Wen-tau Yih, Jianfeng Gao, Li Deng:
Basic Reasoning with Tensor Product Representations. CoRR abs/1601.02745 (2016) - 2014
- [j10]Paul Smolensky, Matthew Goldrick, Donald Mathis:
Optimization and Quantization in Gradient Symbol Systems: A Framework for Integrating the Continuous and the Discrete in Cognition. Cogn. Sci. 38(6): 1102-1138 (2014) - 2013
- [j9]Jennifer Culbertson, Paul Smolensky, Colin Wilson:
Cognitive Biases, Linguistic Universals, and Constraint-Based Grammar Learning. Top. Cogn. Sci. 5(3): 392-424 (2013) - 2012
- [j8]Jennifer Culbertson, Paul Smolensky:
A Bayesian Model of Biases in Artificial Language Learning: The Case of a Word-Order Universal. Cogn. Sci. 36(8): 1468-1498 (2012) - [j7]Geraldine Legendre, Paul Smolensky:
On the Asymmetrical Difficulty of Acquiring Person Reference in French: Production Versus Comprehension. J. Log. Lang. Inf. 21(1): 7-30 (2012) - [c15]Paul Smolensky:
Subsymbolic Computation Theory for the Human Intuitive Processor. CiE 2012: 675-685 - 2010
- [j6]William Bechtel, Marlene Behrmann, Nick Chater, Robert J. Glushko, Robert L. Goldstone, Paul Smolensky:
The Rumelhart Prize at 10. Cogn. Sci. 34(5): 713-715 (2010)
2000 – 2009
- 2008
- [j5]Paul Smolensky:
Introduction to the 2006 Rumelhart Prize Special Issue Honoring Roger Shepard. Cogn. Sci. 32(1): 1-2 (2008) - 2006
- [j4]Paul Smolensky:
Harmony in Linguistic Cognition. Cogn. Sci. 30(5): 779-801 (2006)
1990 – 1999
- 1999
- [j3]Paul Smolensky:
Grammar-based connectionist approaches to language. Cogn. Sci. 23(4): 589-613 (1999) - 1994
- [c14]Paul Smolensky, Bruce Tesar:
Optimality Theory: Universal Grammar, Learning and Parsing Algorithms, and Connectionist Foundations (Abstract). ACL 1994: 271 - 1993
- [c13]Clayton McMillan, Michael Mozer, Paul Smolensky:
Dynamic Conflict Resolution in a Connectionist Rule-Based System. IJCAI 1993: 1366-1373 - 1992
- [c12]Paul Smolensky:
Harmonic Grammars for Formal Languages. NIPS 1992: 847-854 - 1991
- [c11]Clayton McMillan, Michael Mozer, Paul Smolensky:
Rule Induction through Integrated Symbolic and Subsymbolic Processing. NIPS 1991: 969-976 - [c10]Geraldine Legendre, Yoshiro Miyata, Paul Smolensky:
Distributed Recursive Structure Processing. SCAI 1991: 47-53 - 1990
- [j2]Paul Smolensky:
Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems. Artif. Intell. 46(1-2): 159-216 (1990) - [c9]Geraldine Legendre, Yoshiro Miyata, Paul Smolensky:
Distributed Recursive Structure Processing. NIPS 1990: 591-597
1980 – 1989
- 1988
- [c8]Michael Mozer, Paul Smolensky:
Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment. NIPS 1988: 107-115 - 1987
- [j1]Paul Smolensky:
Connectionist AI, symbolic AI, and the brain. Artif. Intell. Rev. 1(2): 95-109 (1987) - [c7]Lucy A. Suchman, William O. Beeman, Michael R. Pear, Barbara A. Fox, Paul Smolensky:
Social science and system design: interdisciplinary collaborations. CHI 1987: 121-123 - [c6]Paul Smolensky, Brigham Bell, Barbara A. Fox, Roger King, Clayton H. Lewis:
Constraint-Based Hypertext for Argumentation. Hypertext 1987: 215-245 - [c5]Paul Smolensky:
Analysis of Distributed Representation of Constituent Structure in Connectionist Systems. NIPS 1987: 730-739 - 1984
- [c4]Rob Kling, Terry Winograd, Paul Smolensky, Roland Schinzinger:
The impact and issues of the fifth generation: Ethical issues in new computing technologies. ACM Annual Conference 1984: 262 - [c3]Paul Smolensky:
Ethical questions and military dominance in next generation computing. ACM Annual Conference 1984: 265 - 1983
- [c2]Paul Smolensky:
Schema Selection and Stochastic Inference in Modular Environments. AAAI 1983: 378-382 - [c1]Claire O'Malley, Paul Smolensky, Liam Bannon, E. Conway, J. Graham, J. Sokolov, Melissa Lee Monty:
A proposal for user centered system documentation. CHI 1983: 282-285
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-28 20:32 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
