Knowledge Base Population (KBP2010) Track
Entity Linking Scoring
We will use the scoring
script (by Paul McNamee)
KBP2009 Entity Linking task.
In contrast to
the 2009 evaluation, a uniform scoring metric will be used, based on
traditional measures of recall, precision, and F-measure, computed from
counts of correct, missing, and spurious responses.
A non-NIL response is correct if it matches a
verified non-NIL entry in the key (the human assessment file);
other non-NIL responses are spurious. A
NIL response where the key has a verified non-NIL
response is considered missing. NIL system responses matching verified
NIL entries in the key are not counted. For
single-valued slots only a single system response will be accepted. For list-valued slots, the verified non-NIL
responses will be grouped into equivalence classes.
Multiple responses to a query must come from
disjoint classes to be counted as correct; other
counted as spurious.
Release 1.1 of the scorer is now available.
To run, download SFScore.java
java SFScore response-file
key-file [flags ...]
where the possible flags are
trace -- print a line
assessment of each
-- judge response based only on answer
string, ignoring doc id
-- ignore case in matching answer string
slots=slotfile -- take list of
pairs from slotfile
of pairs is taken from system response)
The slotfile controls which slots are evaluated; if
you want your system evaluated on all slots for which you generate an
output, the "slots" parameter is not needed. In that case it is
important for your system to generate explicit NILs for slots it cannot
As the key file, you can use one of
the newly produced annotation files, or you can run UpdateSFKey (see
the tools folder)
on the 2009 judgments file.
The anydoc and nocase flags are
designed to make the scorer more useful for development by supporting
soft match, but will not be used for official scoring.
Scorer V1.1 (Final Release): SFScore.java
Scorer V1.0 (Updated to penalize responses marked REDUNDANT in key.): download
Scorer V0.9 (Updated to
use 2010 format files.): download
Scorer V0.8 (First release for
2010, using 2009 format files.): download