Unsupervised Open-Domain Question Answering
This work addresses the high annotation cost in open-domain QA, though it is incremental as it builds on existing unsupervised QA techniques.
The paper tackles the problem of open-domain question answering without labeled data by introducing the first unsupervised approach, achieving up to 86% of the performance of supervised methods.
Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner. However, data annotation cannot also be irresistible for its huge demand in an open domain. Though unsupervised QA or unsupervised Machine Reading Comprehension (MRC) has been tried more or less, unsupervised ODQA has not been touched according to our best knowledge. This paper thus pioneers the work of unsupervised ODQA by formally introducing the task and proposing a series of key data construction methods. Our exploration in this work inspiringly shows unsupervised ODQA can reach up to 86% performance of supervised ones.