Search Results for author:
Found 5 papers, 0 papers with code
LRRA:A Transparent Neural-Symbolic Reasoning Framework for Real-World Visual Question Answering
“The predominant approach of visual question answering (VQA) relies on encoding the imageand question with a ”black box” neural encoder and decoding a single token into answers suchas ”yes” or ”no”.
Improving Entity Linking by Encoding Type Information into Entity Embeddings
“Entity Linking (EL) refers to the task of linking entity mentions in the text to the correct entities inthe Knowledge Base (KB) in which entity embeddings play a vital and challenging role because of the subtle differences between entities.
Improving Low-Resource Named Entity Recognition via Label-Aware Data Augmentation and Curriculum Denoising
“Deep neural networks have achieved state-of-the-art performances on named entity recognition(NER) with sufficient training data while they perform poorly in low-resource scenarios due to data scarcity.
Towards Making the Most of Pre-trained Translation Model for Quality Estimation
DR firstly introduces noise to the target side of parallel data, and the model is trained to detect and recover the introduced noise.
Supervised Contrastive Learning for Cross-lingual Transfer Learning
“Multilingual pre-trained representations are not well-aligned by nature, which harms their performance on cross-lingual tasks.
