13 citations · 17 across the 4 of their papers we have counts for
5 papers · 1 filter
Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification Tasks
Xing Wu, Chaochen Gao, Meng Lin +3
Before entering the neural network, a token is generally converted to the corresponding one-hot representation, which is a discrete distribution of the vocabulary. Smoothed represe…
Data Augmentation for Copy-Mechanism in Dialogue State Tracking
Xiaohui Song, Liangjun Zang, Yipeng Su +3
While several state-of-the-art approaches to dialogue state tracking (DST) have shown promising performances on several benchmarks, there is still a significant performance gap bet…
TransSent: Towards Generation of Structured Sentences with Discourse Marker
Xing Wu, Dongjun Wei, Liangjun Zang +2
Structured sentences are important expressions in human writings and dialogues. Previous works on neural text generation fused semantic and structural information by encoding the e…
"Mask and Infill" : Applying Masked Language Model to Sentiment Transfer
Xing Wu, Tao Zhang, Liangjun Zang +2
This paper focuses on the task of sentiment transfer on non-parallel text, which modifies sentiment attributes (e.g., positive or negative) of sentences while preserving their attr…
Conditional BERT Contextual Augmentation
Xing Wu, Shangwen Lv, Liangjun Zang +2
We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfittin…