no code implementations • 22 Nov 2022 • Yuanpeng Li
Recent improvements from different aspects are discussed.
1 code implementation • 24 Aug 2022 • Yuanpeng Li
In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o. o. d.
1 code implementation • 6 Jan 2022 • Yuanpeng Li, Joel Hestness, Mohamed Elhoseiny, Liang Zhao, Kenneth Church
This paper proposes an efficient approach to learning disentangled representations with causal mechanisms based on the difference of conditional probabilities in original and new distributions.
no code implementations • 8 Feb 2021 • Yuanpeng Li
Compositional generalization is the capacity to recognize and imagine a large amount of novel combinations from known components.
no code implementations • 1 Jan 2021 • Yuanpeng Li, Liang Zhao, Joel Hestness, Ka Yee Lun, Kenneth Church, Mohamed Elhoseiny
To our best knowledge, this is the first work to focus on the transferability of compositionality, and it is orthogonal to existing efforts of learning compositional representations in training distribution.
no code implementations • 1 Jan 2021 • Yuanpeng Li, Liang Zhao, Joel Hestness, Kenneth Church, Mohamed Elhoseiny
In this paper, we argue that gradient descent is one of the reasons that make compositionality learning hard during neural network optimization.
no code implementations • 1 Jan 2021 • Yuanpeng Li
Second, we apply entropy regularization to learn corresponding input components for each output component.
no code implementations • 1 Jan 2021 • Yuanpeng Li
Humans naturally use compositional representations for flexible recognition and expression, but current machine learning lacks such ability.
1 code implementation • ICLR 2020 • Yuanpeng Li, Liang Zhao, Kenneth Church, Mohamed Elhoseiny
It also shows significant improvement in machine translation task.
no code implementations • 15 Mar 2020 • Lei Wang, Wenbin Huang, Yuanpeng Li, Julian Evans, Sailing He
We model and predict human competition behavior by combining many Markov Models with different fixed memory lengths (abbreviated as "multi-AI"), and develop an architecture of multi-AI with changeable parameters to adapt to different competition strategies.
1 code implementation • IJCNLP 2019 • Yuanpeng Li, Liang Zhao, Jian-Yu Wang, Joel Hestness
Compositional generalization is a basic mechanism in human language learning, but current neural networks lack such ability.
no code implementations • 2 Nov 2018 • Yuanpeng Li, Yi Yang, Jian-Yu Wang, Wei Xu
Therefore, toaccelerate this research, we propose a newzero-shot transfer VQA(ZST-VQA)dataset by reorganizing the existing VQA v1. 0 dataset in the way that duringtraining, some words appear only in one module (i. e. questions) but not in theother (i. e. answers).