Implicit Chain of Thought Reasoning via Knowledge Distillation
Yuntian Deng, Kiran Prasad, Roland Fernandez, Paul Smolensky, Vishrav Chaudhary, Stuart Shieber
ArXiv | November 2023, Vol abs/2311.01460
Paul Smolensky
Partner Researcher
Publications
Publications by Year
-
-
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Paul Soulos, Sudha Rao, Caitlin Smith, Eric Rosen, Asli Celikyilmaz, Tom McCoy, Yichen Jiang, Coleman Haley, Roland Fernandez, Hamid Palangi, Jianfeng Gao, Paul Smolensky
ArXiv | August 2022, Vol abs/2208.06061
Neurocompositional computing in human and machine intelligence: A tutorial
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew Goldrick, Jianfeng Gao
MSR-TR-2022-5 | May 2022
Published by Microsoft
52 pages main text, 78 pages total, 11 figures, 2 Appendices, 239 references. For a short presentation of some of this material, see https://arxiv.org/abs/2205.01128 (to appear in AI Magazine).
Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew A. Goldrick, Jianfeng Gao
AI Mag. | May 2022, Vol 43: pp. 308-322
-
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao
North American Chapter of the Association for Computational Linguistics: Human Language Technologies | June 2021
Compositional Processing Emerges in Neural Networks Solving Math Problems
Jacob Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, N. Jojic, Paul Smolensky, Jianfeng Gao
CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference | May 2021, Vol 2021: pp. 1767-1773
-
Learning Inference Rules with Neural TP-Reasoner
Kezhen Chen, Qiuyuan Huang, Paul Smolensky, Kenneth Forbus, Jianfeng Gao
NeurIPS 2020, workshop | December 2020
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
Hassan Akbari, Hamid Palangi, Jianwei Yang, Sudha Rao, Asli Celikyilmaz, Roland Fernandez, Paul Smolensky, Jianfeng Gao, Shih-Fu Chang
ArXiv | November 2020, Vol abs/2011.09530
Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural Representations
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
ICML 2020 | July 2020
-
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao
Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019 | December 2019
TP-N2F: Tensor Product Representation for Natural To Formal Language Generation
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019, workshop | December 2019
Best Paper Award at KR2ML Workshop in NeurIPS 2019.
HUBERT Untangles BERT to Improve Transfer across NLP Tasks
Mehrad Moradshahi, Hamid Palangi, Monica S. Lam, Paul Smolensky, Jianfeng Gao
arxiv | October 2019
https://arxiv.org/abs/1910.12647
-
Tensor Product Generation Networks for Deep NLP Modeling
Qiuyuan Huang, Paul Smolensky, Xiaodong He, Oliver Wu, Li Deng
NAACL 2018 | June 2018
long paper
Learning and analyzing vector encoding of symbolic representations
Roland Fernandez, Asli Celikyilmaz, Rishabh Singh, Paul Smolensky
ICLR 2018 | March 2018
Question-Answering with Grammatically-Interpretable Representations
Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng
AAAI-18: Thirty-Second AAAI Conference on Artificial Intelligence | February 2018
-
Grammatically-Interpretable Learned Representations in Deep NLP Models
Hamid Palangi, Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng
NIPS 2017, Workshop | December 2017
Question-Answering with Grammatically Interpretable Representations
Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng
AAAI-18: Thirty-Second AAAI Conference on Artificial Intelligence | September 2017
-
Symbolic Functions From Neural Computation
Philosophical Transactions of the Royal Society A | January 2012, Vol 370: pp. 3543-3569
-
Optimality: From Neural Networks to Universal Grammar
Alan Prince, Paul Smolensky
Science | March 1997, Vol 275: pp. 1604-1610
-
Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems
Artificial Intelligence | January 1990, Vol 46: pp. 159-216
Publications by Research Area
-
Optimality: From Neural Networks to Universal Grammar
Alan Prince, Paul Smolensky
Science | March 1997, Vol 275: pp. 1604-1610
Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems
Artificial Intelligence | January 1990, Vol 46: pp. 159-216
Implicit Chain of Thought Reasoning via Knowledge Distillation
Yuntian Deng, Kiran Prasad, Roland Fernandez, Paul Smolensky, Vishrav Chaudhary, Stuart Shieber
ArXiv | November 2023, Vol abs/2311.01460
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Paul Soulos, Sudha Rao, Caitlin Smith, Eric Rosen, Asli Celikyilmaz, Tom McCoy, Yichen Jiang, Coleman Haley, Roland Fernandez, Hamid Palangi, Jianfeng Gao, Paul Smolensky
ArXiv | August 2022, Vol abs/2208.06061
Neurocompositional computing in human and machine intelligence: A tutorial
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew Goldrick, Jianfeng Gao
MSR-TR-2022-5 | May 2022
Published by Microsoft
52 pages main text, 78 pages total, 11 figures, 2 Appendices, 239 references. For a short presentation of some of this material, see https://arxiv.org/abs/2205.01128 (to appear in AI Magazine).
Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew A. Goldrick, Jianfeng Gao
AI Mag. | May 2022, Vol 43: pp. 308-322
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao
North American Chapter of the Association for Computational Linguistics: Human Language Technologies | June 2021
Compositional Processing Emerges in Neural Networks Solving Math Problems
Jacob Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, N. Jojic, Paul Smolensky, Jianfeng Gao
CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference | May 2021, Vol 2021: pp. 1767-1773
Learning Inference Rules with Neural TP-Reasoner
Kezhen Chen, Qiuyuan Huang, Paul Smolensky, Kenneth Forbus, Jianfeng Gao
NeurIPS 2020, workshop | December 2020
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
Hassan Akbari, Hamid Palangi, Jianwei Yang, Sudha Rao, Asli Celikyilmaz, Roland Fernandez, Paul Smolensky, Jianfeng Gao, Shih-Fu Chang
ArXiv | November 2020, Vol abs/2011.09530
Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural Representations
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
ICML 2020 | July 2020
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao
Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019 | December 2019
TP-N2F: Tensor Product Representation for Natural To Formal Language Generation
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019, workshop | December 2019
Best Paper Award at KR2ML Workshop in NeurIPS 2019.
HUBERT Untangles BERT to Improve Transfer across NLP Tasks
Mehrad Moradshahi, Hamid Palangi, Monica S. Lam, Paul Smolensky, Jianfeng Gao
arxiv | October 2019
https://arxiv.org/abs/1910.12647
Tensor Product Generation Networks for Deep NLP Modeling
Qiuyuan Huang, Paul Smolensky, Xiaodong He, Oliver Wu, Li Deng
NAACL 2018 | June 2018
long paper
Learning and analyzing vector encoding of symbolic representations
Roland Fernandez, Asli Celikyilmaz, Rishabh Singh, Paul Smolensky
ICLR 2018 | March 2018
Question-Answering with Grammatically-Interpretable Representations
Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng
AAAI-18: Thirty-Second AAAI Conference on Artificial Intelligence | February 2018
Grammatically-Interpretable Learned Representations in Deep NLP Models
Hamid Palangi, Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng
NIPS 2017, Workshop | December 2017
Question-Answering with Grammatically Interpretable Representations
Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng
AAAI-18: Thirty-Second AAAI Conference on Artificial Intelligence | September 2017
Symbolic Functions From Neural Computation
Philosophical Transactions of the Royal Society A | January 2012, Vol 370: pp. 3543-3569
-
Neurocompositional computing in human and machine intelligence: A tutorial
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew Goldrick, Jianfeng Gao
MSR-TR-2022-5 | May 2022
Published by Microsoft
52 pages main text, 78 pages total, 11 figures, 2 Appendices, 239 references. For a short presentation of some of this material, see https://arxiv.org/abs/2205.01128 (to appear in AI Magazine).
Learning Inference Rules with Neural TP-Reasoner
Kezhen Chen, Qiuyuan Huang, Paul Smolensky, Kenneth Forbus, Jianfeng Gao
NeurIPS 2020, workshop | December 2020
Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural Representations
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
ICML 2020 | July 2020
TP-N2F: Tensor Product Representation for Natural To Formal Language Generation
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019, workshop | December 2019
Best Paper Award at KR2ML Workshop in NeurIPS 2019.
HUBERT Untangles BERT to Improve Transfer across NLP Tasks
Mehrad Moradshahi, Hamid Palangi, Monica S. Lam, Paul Smolensky, Jianfeng Gao
arxiv | October 2019
https://arxiv.org/abs/1910.12647
Publications by Type
-
Optimality: From Neural Networks to Universal Grammar
Alan Prince, Paul Smolensky
Science | March 1997, Vol 275: pp. 1604-1610
Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems
Artificial Intelligence | January 1990, Vol 46: pp. 159-216
Implicit Chain of Thought Reasoning via Knowledge Distillation
Yuntian Deng, Kiran Prasad, Roland Fernandez, Paul Smolensky, Vishrav Chaudhary, Stuart Shieber
ArXiv | November 2023, Vol abs/2311.01460
Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Paul Soulos, Sudha Rao, Caitlin Smith, Eric Rosen, Asli Celikyilmaz, Tom McCoy, Yichen Jiang, Coleman Haley, Roland Fernandez, Hamid Palangi, Jianfeng Gao, Paul Smolensky
ArXiv | August 2022, Vol abs/2208.06061
Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew A. Goldrick, Jianfeng Gao
AI Mag. | May 2022, Vol 43: pp. 308-322
Compositional Processing Emerges in Neural Networks Solving Math Problems
Jacob Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, N. Jojic, Paul Smolensky, Jianfeng Gao
CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference | May 2021, Vol 2021: pp. 1767-1773
Neuro-Symbolic Representations for Video Captioning: A Case for Leveraging Inductive Biases for Vision and Language
Hassan Akbari, Hamid Palangi, Jianwei Yang, Sudha Rao, Asli Celikyilmaz, Roland Fernandez, Paul Smolensky, Jianfeng Gao, Shih-Fu Chang
ArXiv | November 2020, Vol abs/2011.09530
HUBERT Untangles BERT to Improve Transfer across NLP Tasks
Mehrad Moradshahi, Hamid Palangi, Monica S. Lam, Paul Smolensky, Jianfeng Gao
arxiv | October 2019
https://arxiv.org/abs/1910.12647
Symbolic Functions From Neural Computation
Philosophical Transactions of the Royal Society A | January 2012, Vol 370: pp. 3543-3569
-
Neurocompositional computing in human and machine intelligence: A tutorial
Paul Smolensky, R. Thomas McCoy, Roland Fernandez, Matthew Goldrick, Jianfeng Gao
MSR-TR-2022-5 | May 2022
Published by Microsoft
52 pages main text, 78 pages total, 11 figures, 2 Appendices, 239 references. For a short presentation of some of this material, see https://arxiv.org/abs/2205.01128 (to appear in AI Magazine).
-
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao
North American Chapter of the Association for Computational Linguistics: Human Language Technologies | June 2021
Learning Inference Rules with Neural TP-Reasoner
Kezhen Chen, Qiuyuan Huang, Paul Smolensky, Kenneth Forbus, Jianfeng Gao
NeurIPS 2020, workshop | December 2020
Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural Representations
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
ICML 2020 | July 2020
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao
Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019 | December 2019
TP-N2F: Tensor Product Representation for Natural To Formal Language Generation
Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao
Thirty-third Conference on Neural Information Processing Systems (NeurIPS) 2019, workshop | December 2019
Best Paper Award at KR2ML Workshop in NeurIPS 2019.
Tensor Product Generation Networks for Deep NLP Modeling
Qiuyuan Huang, Paul Smolensky, Xiaodong He, Oliver Wu, Li Deng
NAACL 2018 | June 2018
long paper
Learning and analyzing vector encoding of symbolic representations
Roland Fernandez, Asli Celikyilmaz, Rishabh Singh, Paul Smolensky
ICLR 2018 | March 2018
Question-Answering with Grammatically-Interpretable Representations
Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng
AAAI-18: Thirty-Second AAAI Conference on Artificial Intelligence | February 2018
Grammatically-Interpretable Learned Representations in Deep NLP Models
Hamid Palangi, Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng
NIPS 2017, Workshop | December 2017
Question-Answering with Grammatically Interpretable Representations
Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng
AAAI-18: Thirty-Second AAAI Conference on Artificial Intelligence | September 2017