There has been a significant progress in thefield of extractive question answering (EQA)in the recent years. However, most of themrely on annotations of answer-spans in the cor-responding passages. In this work, we ad-dress the problem of EQA when no annotations are present for the answer span, i.e.,when the dataset contains only questions andcorresponding passages. Our method is basedon auto-encoding of the question that performsa question answering (QA) task during encoding and a question generation (QG) task duringdecoding. Our method performs well in a zero-shot setting and can provide an additional lossto boost performance for EQA.