The task of few-shot extractive question-answering aims to extract real answer fragments using the given context of the article.The method employed by its baseline model focuses solely on learning spans,lacking the utilization of global semantic information.This approach exhibits comprehension biases,especially in instances involving multiple sets of distinct repeated spans.Therefore,this paper proposes a multi-label semantic calibration method for few-shot extractive QA to mitigate the above issues.Specifically,this method uses the head label,which contains global semantic information,and the special character in the baseline model to form a multi-label for semantic fusion.The semantic fusion gate is then used to control the introduction of global information flow to integrate global seman-tic information into the semantic information of the special character.Next,the semantic selection gate is used to retain or replace the newly integrated global semantic information and the original semantic information of the special character,achieving semantic adjust-ment of label bias.The results of 56 experiments on 8 few-shot extractive QA datasets consistently outperformed the baseline model in terms of the evaluation metric F1 score.This demonstrates the effectiveness and advancement of the method.
维普
万方数据