We found a potential increase of 35 % in
<term>
MRR
</term>
with respect to the original question .
#11728We found a potential increase of 35% inMRR with respect to the original question.
other,13-3-N06-2009,ak
We investigate that claim by adopting a simple
<term>
MT-based paraphrasing technique
</term>
and evaluating
<term>
QA system performance
</term>
on paraphrased questions .
#11712We investigate that claim by adopting a simple MT-based paraphrasing technique and evaluatingQA system performance on paraphrased questions.
other,17-1-N06-2009,ak
State-of-the-art
<term>
Question Answering ( QA ) systems
</term>
are very sensitive to variations in the phrasing of an
<term>
information need
</term>
.
#11683State-of-the-art Question Answering (QA) systems are very sensitive to variations in the phrasing of aninformation need.
other,7-2-N06-2009,ak
Finding the preferred language for such a
<term>
need
</term>
is a valuable task .
#11693Finding the preferred language for such aneed is a valuable task.
tech,1-1-N06-2009,ak
State-of-the-art
<term>
Question Answering ( QA ) systems
</term>
are very sensitive to variations in the phrasing of an
<term>
information need
</term>
.
#11667State-of-the-artQuestion Answering ( QA ) systems are very sensitive to variations in the phrasing of an information need.
tech,8-3-N06-2009,ak
We investigate that claim by adopting a simple
<term>
MT-based paraphrasing technique
</term>
and evaluating
<term>
QA system performance
</term>
on paraphrased questions .
#11707We investigate that claim by adopting a simpleMT-based paraphrasing technique and evaluating QA system performance on paraphrased questions.