|
sentence plan
</term>
whose
<term>
rating
</term>
on
|
average
|
is only 5 % worse than the
<term>
top human-ranked
|
#1448
We show that the trained SPR learns to select a sentence plan whose rating on average is only 5% worse than the top human-ranked sentence plan. |
measure(ment),35-4-N03-1004,bq |
32.8 % improvement according to the
<term>
|
average
|
precision metric
</term>
. In this paper
|
#2431
Experiments evaluating the effectiveness of our answer resolution algorithm show a 35.0% relative improvement over our baseline system in the number of questions correctly answered, and a 32.8% improvement according to theaverage precision metric. |
measure(ment),13-7-P03-1050,bq |
indicates an improvement of 22-38 % in
<term>
|
average
|
precision
</term>
over
<term>
unstemmed text
|
#4582
Task-based evaluation using Arabic information retrieval indicates an improvement of 22-38% inaverage precision over unstemmed text, and 96% of the performance of the proprietary stemmer above. |
measure(ment),19-5-N04-4028,bq |
multi-field records
</term>
, obtaining an
<term>
|
average
|
precision
</term>
of 98 % for retrieving
|
#6877
We implement several techniques to estimate the confidence of both extracted fields and entire multi-field records, obtaining anaverage precision of 98% for retrieving correct fields and 87% for multi-field records. |
measure(ment),6-2-P05-1032,bq |
computational complexity
</term>
and
<term>
|
average
|
retrieval times
</term>
for looking up
<term>
|
#9163
We detail the computational complexity andaverage retrieval times for looking up phrase translations in our suffix array-based data structure. |