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 IELTS, a challenging academic English examination for English
learners who are not the native English speakers. 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.
With the popularity of shared videos, social networks, on-line courses,
and the like, the quantity of multimedia or spoken content is growing
much faster than what human being scan view or listen to. A user can
scan through text easily, but it is not the case for spoken content
because they cannot be directly displayed on-screen. Therefore,
accessing large collections of multimedia or spoken content is difficult
and time-consuming for humans. Hence, it is desirable that machines
automatically listen to and understand spoken content, and extract or
even visualize the key information for humans.
https://ecsielts.com/
No comments:
Post a Comment