Label Embedding

AbstractDistantly-supervised relation extraction has proven to be effective to find relational facts from texts. However, the existing approaches treat labels as independent and meaningless one-hot vectors, which cause a loss …...

With pre-trained models, such as BERT, gain- ing more and more attention, plenty of re- search has been done to further promote their capabilities, from enhancing the experimental procedures (Sun …...

AbstractEmotion cause analysis (ECA) aims to identify the potential causes behind certain emotions intext. Lots of ECA models have been designed to extract the emotion cause at the clause level. …...