Unsupervised Commonsense Question Answering Via Negative Samples Enhancement
In contrast to the popular issue of question generation in unsupervised commonsense question-answering,this paper proposes an unsupervised commonsense question-answering model via distractor options enhancement.In our method,questions and correct answers are first generated according to the knowledge triples.Then the corre-sponding question subgraph is established for each question to obtain the knowledge triples related to the question.The attention mechanism is used to decide the distractors according to the questions and correct answers.Finally,the generated data with enhanced distractors are used to train the question-answering model.The experiment results show the model is superior to the latest methods on four different types of tasks.
万方数据
维普
