Yongyi Mao
6 papers in the PaperMetrix corpus
Papers by this author
-
MixUp as Locally Linear Out-of-Manifold Regularization
2019 · Proceedings of the AAAI Conference on Artificial Intelligence
MixUp (Zhang et al. 2017) is a recently proposed dataaugmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with such additional …
-
Parallel Interactive Networks for Multi-Domain Dialogue State Generation
2020 · arXiv (Cornell University)
The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) models. In this study, we argue that the incorporation …
-
On Scalar Embedding of Relative Positions in Attention Models
2021 · Proceedings of the AAAI Conference on Artificial Intelligence
Attention with positional encoding has been demonstrated as a powerful component in modern neural network models, such as transformers. However, why positional encoding works well in attention models remains largely unanswered. In this paper, we …
-
On the Softmax Bottleneck of Recurrent Language Models
2021 · Proceedings of the AAAI Conference on Artificial Intelligence
Recent research has pointed to a limitation of word-level neural language models with softmax outputs. This limitation, known as the softmax bottleneck refers to the inability of these models to produce high-rank log probability (log …
-
Hierarchical Modeling of Label Dependency and Label Noise in Fine-grained Entity Typing
2021
Fine-grained entity typing (FET) aims to annotate the entity mentions in a sentence with fine-grained type labels. It brings plentiful semantic information for many natural language processing tasks. Existing FET approaches apply hard attention to …
-
Intrusion-Free Graph Mixup
2021 · arXiv (Cornell University)
We present a simple and yet effective interpolation-based regularization technique to improve the generalization of Graph Neural Networks (GNNs). We leverage the recent advances in Mixup regularizer for vision and text, where random sample pairs …