Search Results for author:
Found 3 papers, 0 papers with code
Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models
We then traina model with a primary contrastive objective; to this stan-dard configuration, we add a simple output head trained topredict the attentional map for each image, guided by thepseudo labels from teacher model.
Context-aware Sentiment Word Identification: sentiword2vec
Because of its great performance in representing inter-word relation, we use sentiment word vectors to identify the special words.
Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation
Recurrent neural network(RNN) has been broadly applied to natural language processing(NLP) problems.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
