tech,1-1-N06-2009,bq its performance . State-of-the-art <term> Question Answering ( QA ) systems </term> are very sensitive to variations
other,17-1-N06-2009,bq to variations in the phrasing of an <term> information need </term> . Finding the preferred <term> language
other,3-2-N06-2009,bq need </term> . Finding the preferred <term> language </term> for such a <term> need </term> is a valuable
other,7-2-N06-2009,bq preferred <term> language </term> for such a <term> need </term> is a valuable task . We investigate
tech,8-3-N06-2009,bq investigate that claim by adopting a simple <term> MT-based paraphrasing technique </term> and evaluating <term> QA system </term>
tech,13-3-N06-2009,bq paraphrasing technique </term> and evaluating <term> QA system </term> performance on <term> paraphrased questions
other,17-3-N06-2009,bq <term> QA system </term> performance on <term> paraphrased questions </term> . We found a potential increase of
measure(ment),9-4-N06-2009,bq found a potential increase of 35 % in <term> MRR </term> with respect to the original <term>
other,15-4-N06-2009,bq </term> with respect to the original <term> question </term> . There are several approaches that
skrij podrobnosti