Machine comprehension (MC) and question answering (QA) are crucial tasks in natural language understanding. Training deep neural network-based QA models has become practical upon the recent release of the Stanford Question Answering Dataset (SQuAD), a significantly larger dataset of question-answer pairs created by humans on a set of Wikipedia articles [1]. In this paper, we propose an end-to-e...

As part of the task of automated question answering from a large collection of text documents, the reduction of the search space to a smaller set of document passages that are actually searched for answers constitutes a difficult but rewarding research issue. We propose a set of precision-enhancing filters for passage retrieval based on semantic constraints detected in the submitted questions. ...

At the time of the visit of Their Majesties KingGeorge and Qneen Mary to Calcutta in January 1912 the question was asked by one high up in authority what has the Indian Medical Service done for India ? At the time there was but little difficulty in giving a short answer to the question, and later Sir R. Havelock Charles, G.c.v.o. (not the least distinguished of the many I. M. S. names whom we h...