18 citations · 46 across the 15 of their papers we have counts for
3 papers · 1 filter
Semantic Label Smoothing for Sequence to Sequence Problems
Michal Lukasik, Himanshu Jain, Aditya Krishna Menon +4
Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising. However, extending such method…
Text Segmentation by Cross Segment Attention
Michal Lukasik, Boris Dadachev, Gonçalo Simões +1
Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream tasks such as informa…
Does label smoothing mitigate label noise?
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon +1
Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to im…