tool,19-2-N01-1003,bq |
methodology for automatically training
<term>
|
SPoT
|
</term>
on the basis of
<term>
feedback
</term>
|
#1354
In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges. |
other,24-2-N01-1003,bq |
training
<term>
SPoT
</term>
on the basis of
<term>
|
feedback
|
</term>
provided by
<term>
human judges
</term>
|
#1359
In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges. |
other,20-5-N01-1003,bq |
, and then selects the top-ranked
<term>
|
plan
|
</term>
. The
<term>
SPR
</term>
uses
<term>
ranking
|
#1420
Second, the sentence-plan-ranker (SPR) ranks the list of output sentence plans, and then selects the top-ranked plan . |
tech,1-6-N01-1003,bq |
top-ranked
<term>
plan
</term>
. The
<term>
|
SPR
|
</term>
uses
<term>
ranking rules
</term>
automatically
|
#1423
The SPR uses ranking rules automatically learned from training data. |
tech,5-7-N01-1003,bq |
</term>
. We show that the trained
<term>
|
SPR
|
</term>
learns to select a
<term>
sentence
|
#1438
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),13-7-N01-1003,bq |
a
<term>
sentence plan
</term>
whose
<term>
|
rating
|
</term>
on average is only 5 % worse than
|
#1446
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. |