Meng Lin, Chaochen Gao, Xing Wu, Songlin Hu, Liangjun Zang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Before entering the neural network, a token is generally converted to the corresponding onehot representation, which is a discrete distribution of the vocabulary. Smoothed representation is the probability of candidate tokens obtained from a pre-trained masked language model, which can be seen as a more informative substitution to the one-hot representation. We propose an efficient data augmentation method, termed text smoothing, by converting a sentence from its one-hot representation to a controllable smoothed representation. We evaluate text smoothing on different benchmarks in a low-resource regime. Experimental results show that text smoothing outperforms various mainstream data augmentation methods by a substantial margin. Moreover, text smoothing can be combined with those data augmentation methods to achieve better performance. Our code are available at https://github.com/caskcsg/TextSmoothing.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2202.13840")
get_code_for_paper("2202.13840")
have("2202.13840")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2202.13840.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2202.13840)
Connect an agent — have() is free.