A user can scan through a text easily, but it is not the case for spoken content, because they cannot be directly displayed on-screen. As a result, accessing large collections of spoken con-tent is much more difficult and time-consuming than doing so for the text content. It would therefore be helpful to develop machines that understand spoken content. In this paper, we propose two new tasks for machine comprehension of spoken content. The first is a listening comprehension test for BEC, a challenging academic English examination for English learners who are not the native English speakers. How to Listening Test and Spoken BEC
We show that the proposed model out performs the naive approaches and other neural network based models by exploiting the hierarchical structures of natural languages and the selective power of attention mechanism. For the second listening comprehension task – spoken squad we find that speech recognition errors severely impair machine comprehension; we propose the use of sub word units to mitigate the impact of these errors.