15 citations · 15 across the 6 of their papers we have counts for
6 papers
Learning Action Conditions from Instructional Manuals for Instruction Understanding
Te-Lin Wu, Caiqi Zhang, Qingyuan Hu +2
The ability to infer pre- and postconditions of an action is vital for comprehending complex instructions, and is essential for applications such as autonomous instruction-guided a…
Can Model Compression Improve NLP Fairness
Guangxuan Xu, Qingyuan Hu
Model compression techniques are receiving increasing attention; however, the effect of compression on model fairness is still under explored. This is the first paper to examine th…
Modeling Fuzzy Cluster Transitions for Topic Tracing
Xiaonan Jing, Yi Zhang, Qingyuan Hu +1
Twitter can be viewed as a data source for Natural Language Processing (NLP) tasks. The continuously updating data streams on Twitter make it challenging to trace real-time topic e…
Tracing Topic Transitions with Temporal Graph Clusters
Xiaonan Jing, Qingyuan Hu, Yi Zhang +1
Twitter serves as a data source for many Natural Language Processing (NLP) tasks. It can be challenging to identify topics on Twitter due to continuous updating data stream. In thi…
Exploring Lexical Irregularities in Hypothesis-Only Models of Natural Language Inference
Qingyuan Hu, Yi Zhang, Kanishka Misra +1
Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) is the task of predicting the entailment relation between a pair of sentences (premise and hypothesis). Thi…
Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer
Qian Li, Qingyuan Hu, Yong Qi +3
Data augmentation have been intensively used in training deep neural network to improve the generalization, whether in original space (e.g., image space) or representation space. A…