Капсула желісі

AbstractWhile much progress has been made in how to encode a text sequence into a sequence of vectors, less attention has been paid to how to aggregate these preceding vectors …...

AbstractAspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context. The main challenge comes from multi-aspect sentences, …...

AbstractThis paper describes a novel research approach to detect type and target of offensive posts in social media using a capsule network. The input to the network was character embeddings …...

AbstractBeing able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling …...

AbstractDistantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts. However, the automatically established training datasets in distant supervision contain …...

AbstractThis paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware …...

AbstractBuilding an interpretable AI diagnosis system for breast cancer is an important embodiment ofAI assisted medicine. Traditional breast cancer diagnosis methods based on machine learning areeasy to explain but the …...