English noun-verb ambiguity

[Brian MacWhinney]

Dear ChiBolts,

One of the few remaining inaccuracies with English POST involves the task of disambiguating unmarked nouns and verbs.  Errors in this area are particularly frustrating when one of the forms is very rare, such as the reading of “finger” as a verb.  It is a shame to allow this occasional rare usage to interfere with the much more common nominal usage.  To address this, I have implemented a method of transcribing about 30 nouns as nxnoun, as in “nxlook" for the word “look” as a noun and “vxfinger" for the word “finger” as a verb.  The relevant forms are given in the files nx.cut and vx.cut in the ENG lexicon.

This places the responsibility of spotting these rare forms on the transcriber.  This is only necessary for the unmarked forms of these words and for ones with final –s, like “fingers".  For the form vxfinger, MOR will produce “v|vxfinger” Afterwards, we can then use a POSTMORTEM rule to change this to “v|finger”.

For many purposes this level of tagging accuracy may not be necessary.  However, it allows MOR to increase accuracy from about 96% to a bit over 97%.

— Brian MacWhinney

-- 
You received this message because you are subscribed to the Google Groups "chibolts" group.
To unsubscribe from this group and stop receiving emails from it, send an email to chibolts+unsubscribe at googlegroups.com.
To post to this group, send email to chibolts at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/chibolts/C0676560-9E04-4703-A8F8-2E662A429055%40cmu.edu.
For more options, visit https://groups.google.com/d/optout.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/chibolts/attachments/20151123/e0e6c358/attachment.htm>