[Lexicog] Word context

Marie-Odile Junker mojunker at CCS.CARLETON.CA
Thu May 13 09:08:46 UTC 2004


Dear Simeon,
I think the context is much more, especially for oral languages, I believe
we have to get out of this textual discourse analysis tradition. Context is
more than language. It is everything in the environment surrounding the
speech-act: It includes environmental, cultural and interpersonal knowledge
(i.e the high-context culture vs low-context culture). This being said,
Shoebox or the SIL old Mac concordance program will do the kind of textual
context that what you want.
You could also you could extract some statistics about a word's
collocations. Some of this has been done for a bilingual English-Inuktitut
corpus by Joel Martin's team at the National Research Center of Canada:
See below the abstract of a talk Joel Martin gave at our Cog Sci seminar
last year.
---------------------------------------------------------------------------------------------------------------------------------------

Joel Martin, Institute for Information Technology, National Research Council
Canada, speaker for the final Cognitive Science Research, Carleton
University, April 17, 2003.

Title: Aligning and Using an English-Inuktitut Parallel Corpus

Abstract: A parallel corpus of texts in English and in Inuktitut, an Inuit
language, is presented. These texts are from the Nunavut Hansards of Canada.
The parallel texts are processed in two phases, the sentence alignment phase
and the word correspondence phase. Our sentence alignment technique achieves
a precision of 91.4% and a recall of 92.3%. Our word correspondence
technique is aimed at providing the broadest coverage collection of reliable
pairs of Inuktitut and English morphemes for dictionary expansion. For an
agglutinative language like Inuktitut, this entails considering substrings,
not simply whole words. We employ a Pointwise Mutual Information method
(PMI) and attain a coverage of 72.3% of English words and a precision of
87%. (work done with Howard Johnson, Benoit Farley, and Anna Maclachlan)
--------------------------------------------------------------------------------------------------------------------------------

At 06:37 PM 5/12/2004 +0000, you wrote:
>I am currently trying to develop a software to extract words a
>document.I wnat to extract the word and its context so that I can
>use that for translation later.I have a problem trying to figure out
>what the word "context" meangs.Can anyone help me to identify what
>is the context of a word, is it the meaning or the sentence it
>appears from??

Marie-Odile Junker
Associate Professor of Linguistics
French Department and Cognitive Science Program
Carleton University
Ottawa, CANADA K1S 5B6
Tel: (613) 520-2600 x 7601
e-mail:mojunker at ccs.carleton.ca
Web page: http://www.carleton.ca/~mojunker/

See the interactive East Cree language project: http://www.eastcree.org



------------------------ Yahoo! Groups Sponsor ---------------------~-->
Make a clean sweep of pop-up ads. Yahoo! Companion Toolbar.
Now with Pop-Up Blocker. Get it for free!
http://us.click.yahoo.com/L5YrjA/eSIIAA/yQLSAA/HKE4lB/TM
---------------------------------------------------------------------~->


Yahoo! Groups Links

<*> To visit your group on the web, go to:
     http://groups.yahoo.com/group/lexicographylist/

<*> To unsubscribe from this group, send an email to:
     lexicographylist-unsubscribe at yahoogroups.com

<*> Your use of Yahoo! Groups is subject to:
     http://docs.yahoo.com/info/terms/



More information about the Lexicography mailing list