SIGPARSE 96
International Workshop on PUNCTUATION IN COMPUTATIONAL LINGUISTICS
Friday, June 28, 1996
in conjunction with the 34th Annual Meeting of the
Association for Computational Linguistics
University of California, Santa Cruz
Santa Cruz, California, USA
FOCUS OF THE WORKSHOP
Surprisingly, most research in Computational Linguistics over the
years has almost completely ignored the (ortho)graphical facet of
language, punctuation. This has mainly been due to the overall
complexity of that field, but also due to the lack of a good
theoretical description of the problem.
However, interest in punctuation in the fields of `straight' and
computational linguistics has greatly increased in the last five
years. This is partially due to the publication, in 1990, of Geoffrey
Nunberg's book "The Linguistics of Punctuation", but also due to the
fact that it has been recognised that true understanding and
processing of written language will be almost impossible if
punctuation is not taken into account.
Almost any structure-giving, or graphical, device in text could be
described as punctuation - this means that punctuation falls into
roughly three categories:
Within word: marks like hyphens and apostrophes
Between word: what we conventionally think of as punctuation,
e.g. commas, full-stops, colons.
Higher-level graphical punctuation: paragraphing, indentation,
underlining, font changes etc...
Although most research on punctuation seems to have focussed on the
narrow, second definition, and its role in parsing and syntax,
punctuation has a far wider nature and application, and there is
interest in fields as diverse as semantics, discourse, automatic
editing, conversation analysis, intonation and psycholinguistics.
The time is therefore ripe for a workshop in the general field of
punctuation, to bring together all those researchers who have been
working on various aspects of the problem, or who have an interest in
it, to share ideas and maybe establish some standard approach to what
is a novel and highly interesting area.
WORKSHOP ORGANISATION
The workshop will be a full-day event consisting of about 12 half-hour
papers, including some time for discussion. There will be an invited
talk given by the `Father of Modern Punctuation Research', Geoff
Nunberg of Xerox PARC.
SUBMISSIONS
Submissions are invited that address the issue of punctuation in all
areas of CL, including, but not limited to, the following:
Parsing Syntax Generation
Discourse processing Semantics Machine translation
Phonetics Phonology Corpus-based work
Psycholinguistics Message understanding Editorial assistants
Information retrieval Statistical methods Automated tagging
Papers should not exceed 3,200 words and should include an abstract of
not more than 15 lines. The title page should include title, authors,
addresses, email, telephone numbers and the abstract. Electronic
submissions are strongly prefered and encouraged, and should be in
postscript, self-contained LaTeX or (if nothing else is available) in
ASCII.
Submissions and any questions should be sent to:
Bernie Jones Centre for Cognitive Science,
2 Buccleuch Place,
bernie@cogsci.ed.ac.uk Edinburgh EH8 9LW, United Kingdom
DEADLINES
Submissions should reach Bernie Jones by Friday 12th April 1996.