Alert button
Picture for Nitish Keskar

Nitish Keskar

Alert button

Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality

Add code
Bookmark button
Alert button
Oct 24, 2020
Gustavo Aguilar, Bryan McCann, Tong Niu, Nazneen Rajani, Nitish Keskar, Thamar Solorio

Figure 1 for Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality
Figure 2 for Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality
Figure 3 for Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality
Figure 4 for Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality
Viaarxiv icon

Improving out-of-distribution generalization via multi-task self-supervised pretraining

Add code
Bookmark button
Alert button
Mar 30, 2020
Isabela Albuquerque, Nikhil Naik, Junnan Li, Nitish Keskar, Richard Socher

Figure 1 for Improving out-of-distribution generalization via multi-task self-supervised pretraining
Figure 2 for Improving out-of-distribution generalization via multi-task self-supervised pretraining
Figure 3 for Improving out-of-distribution generalization via multi-task self-supervised pretraining
Figure 4 for Improving out-of-distribution generalization via multi-task self-supervised pretraining
Viaarxiv icon