Table of Contents
cntlist - file listing number of times each tagged sense occurs
in a semantic concordance
A cntlist file for a semantic concordance
lists the number of times each semantically tagged sense occurs in the
concordance and its sense number in the WordNet database. Each line in
the file corresponds to a sense in the WordNet database to which at least
one semantic tag points. Only senses that are tagged in a concordance
are in the concordance's cntlist file. See semcor(7WN)
for information
about semantic concordances and a list of those included in this release.
A file, cntlist , is provided with each semantic concordance for informational
and statistical purposes only. The files are not used by any software
provided with the WordNet or semantic concordance packages. A cntlist
file is generated by counting the number of sent_num,word_num pairs in
all location_list s for each sense_key in a taglist(5WN)
file. The data
is sorted in descending numerical order, and the resulting file ranks
the senses from most to least frequently tagged in the semantic concordance.
In the WordNet database, words are assigned
sense numbers based on frequency of use in the semantic concordances.
The cntlist file used by grind(1WN)
to build the WordNet database and
assign the sense numbers is a union of the cntlist files from the various
semantic concordances. This combined cntlist file is provided with the
WordNet package and is found in the WNSEARCHDIR directory.
Each line in a cntlist file contains information for one sense. The file
is ordered from most to least frequently tagged sense. The fields are
separated by one space, and each line is terminated with a newline character.
Senses having the same tag_cnt value are listed in reverse alphabetical
order of the lemma field of the sense_key .
Each line in cntlist is
of the form:
tag_cnt sense_key sense_number
where tag_cnt is the
decimal number of times the sense is tagged in the corresponding semantic
concordance. sense_key is a WordNet sense encoding and sense_number
is a WordNet sense number as described in senseidx(5WN)
.
- WNHOME
- Base directory for WordNet. Unix default is /usr/local/wordnet1.6
, PC default is C:\wn16 , Macintosh default is : .
- WNSEARCHDIR
- Directory
in which the WordNet database has been installed. Unix default is WNHOME/dict
, PC default is WNHOME\dict , Macintosh default is :Database .
- SEMCORDIR
- Directory in which the semantic concordance package has been installed.
Unix default is WNHOME/semcor , PC default is WNHOME\semcor , Macintosh
default is :Semcor .
In directory SEMCORDIR/conc on Unix platforms,
SEMCORDIR\conc on PC platforms, and SEMCORDIR:conc on Macintosh platforms:
- cntlist
- file listing number of times each tagged sense occurs in semantic
concordance conc
In directory WNSEARCHDIR :
- cntlist
- file of combined
semantic concordance cntlist files. Used to assign sense numbers in WordNet
database
grind(1WN)
, senseidx(5WN)
, taglist(5WN)
, semcor(7WN)
.
Table of Contents