[CWB] About using CQP to collect the co-occurrence.
(Ray) Liangping Wu
liangpingwu at 126.com
Sat Mar 29 07:48:36 CET 2014
You may try the collocations function (at the top right corner) after either a Standard query or a Restricted query.
For instance, the collocates of interesting in Dickens are:
|
No.
|
Word
|
Total no. in whole corpus
|
|
1
|
,
|
282,600
|
|
2
|
the
|
142,788
|
|
3
|
and
|
100,640
|
|
4
|
.
|
114,392
|
|
5
|
of
|
74,054
|
|
6
|
most
|
2,411
|
|
7
|
to
|
73,351
|
|
8
|
an
|
7,878
|
|
9
|
was
|
33,419
|
|
10
|
a
|
63,499
|
|
11
|
in
|
47,553
|
|
12
|
very
|
8,508
|
|
13
|
this
|
12,613
|
Best,
Ray
At 2014-03-28 23:19:57,"李吉明" <jimingli78 at gmail.com> wrote:
Hi, everyone. I'm a newbie to use CQP query language.
And I want to use it to collect word co-occurrences.
Take the DICKENS corpus as an example:
Given a search string "interesting"
I want to get the word co-occurrence in the same sentence (or a window like 5 words) of "interesting"', like below:
the 21
most 20
an 16
Thank you very much.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://devel.sslmit.unibo.it/pipermail/cwb/attachments/20140329/68bfe476/attachment.html>
More information about the CWB
mailing list