qq_36242451的博客

Neuralnetworkbasedmethodshaveobtainedgreat progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we use the multitasklearningframeworktojointlylearnacrossmultiple related tasks. Based on recurrent neural network, we propose three different mechanisms of sharinginformationtomodeltextwithtask-specific and shared layers. The entire network is trained jointly on all these tasks. Experiments on four benchmark text classification tasks show that our proposedmodelscanimprovetheperformanceofa task with the help of other related tasks.