Question Entailment on Developing Indonesian Covid-19 Question Answering System

Despite the severe impact of COVID-19 on humans has already decreased, people still need to be aware recent disease information. A continually updated Frequently Asked Questions (FAQ) system could help public get valid and relevant To maintain a FAQ manually needs much effort, hence an approach develop automatically is needed. Question Answering System (QAS) that can accept input in question sentences produces answer quickly, concisely, relevantly, used provide information public. One method developing QAS Recognizing Entailment (RQE). RQE form relationship based cause-and-effect between two pieces text called (T) hypothesis (H). We present study Covid-19 Bahasa Indonesia using RQE. The datasets are collected from reputable sources consist 725 pairs questions answers. experimental results show best performance were obtained Logistic Regression model training set 1, which contains 54.2% positive 45.8% negative with f-measure value 83.65%. These indicate identify entailment new dataset well.