Corpora: Correction to: Summary of Responses to "UNIQUE NLP" (and

Eduard Hovy (hovy@ISI.EDU)
Wed, 9 Sep 1998 10:10:09 -0800

The following somewhat misleading message was posted on Tue, 8 Sep 1998:

>X-Sender: annes@mana.htdc.org
>Subject: Corpora: Summary of Responses to "UNIQUE NLP" (and CONCLUSION)
>Sender: owner-corpora@lists.uib.no
>Precedence: bulk
>
>SUMMARY
>About two weeks ago I requested information concerning NLP
>software that offered the ability to do a q&a exchange
>between animations and a user similar to the "ChatterBox"
>software (free) we have at http://www.haptek.com. Here is
>a summary of the responses I got
>
>2.
>The Information Science Institute at USC (www.isi.edu) did a lot of
>work in that area about 10 years ago, using, I believe, their PENMAN
>syntax analyzer. I think the project was lead by Ed Hovy, who was
>still a director there last year but seems to have left since. There
>was also a Dr. Christiensen (spelling?) but he has returned to
>Australia, probably at McQuarrie University with MAK Halliday. Not
>much help, but you can try emailing ISI staff: some may remember.

There is, and has been for about two decades, an active research group
in NLP at USC's Information Sciences Institute (ISI). The PENMAN
system, a natural language *generator*, was developed from circa 1979
to 1986 in a project led by Bill Mann and Christian Matthiessen; Mann
has since retired and Matthiessen is a professor of Linguistics at
Macquarie University in Melbourne, Australia (cmatthie@pip.engl.mq.edu.au).

The NLP Group at ISI currently contains several complementary projects.
More recent research at ISI includes:

1. Machine Translation (the Japangloss/GAZELLE system): Japanese, Arabic,
and Spanish to English, using a hybridization of statistical and symbolic
techniques. Contact Kevin Knight (knight@isi.edu).

2. Text Summarization (the SUMMARIST system): multilingual summarization
using several complementary techniques, including discourse structure.
Contact Eduard Hovy (hovy@isi.edu) and Daniel Marcu (marcu@isi.edu).

3. Multilingual Information Management (the MuST and C*ST*RD systems):
this work includes multilingual Information Retrieval, clustering, and
so on; contact Chin-Yew Lin (cyl@isi.edu).

4. Construction of large ontologies and lexicons: the semi-automated
merging of large ontologies, and the enhancement of these using information
extracted out of dictionaries and the web; contact Eduard Hovy (hovy@isi.edu).

5. Sentence Planning and Generation (the HealthDoc Sentence Planner and
the NITROGEN system): the pre-realization stage of microplanning sentence
structure and content, using a variety of methods; contact Eduard Hovy
(hovy@isi.edu). For realization, NITROGEN combines a phrase structure
grammar with a bigram model of English to generate from underspecified
input; contact Kevin Knight (knight@isi.edu).

More information on all this is available from
http://www.isi.edu/natural-language/nlp-at-isi.html

E

----------------------------------------------------------------------------
Eduard Hovy
email: hovy@isi.edu USC Information Sciences Institute
tel: 310-822-1511 ext 731 4676 Admiralty Way
fax: 310-823-6714 Marina del Rey, CA 90292-6695
project homepage: http://www.isi.edu/natural-language/nlp-at-isi.html