LINGUIST List 9.1099

Sun Aug 2 1998

Calls: Lexical Semantic Tagging, CL Journal

Editor for this issue: Martin Jacobsen <martylinguistlist.org>

Directory

1. Priscilla Rasmussen, Lexical Semantic Tagging
2. Kemal Oflazer, Special Issue of CL Journal-Finite State Methods in NLP

Lexical Semantic Tagging
A Special Issue of the Journal of Natural Language Engineering

Guest Editors:
Marc Light and Martha Palmer


		 CALL FOR PAPERS	 


 NOTE: Deadline for submissions is November 1st, 1998

Computing semantic representations is crucial for many applications of
natural language processing. Currently, semantic lexicons and sets of
semantic composition rules are hand-crafted by the designers of the
NLP system. The difficulty of building such hand-crafted semantic
knowledge bases has limited the field of NLP to applications that can
be contained within well-defined subdomains. The likely escape from
this limitation will come from the use of automated or semi-automated
methods of lexical acquisition. However, the field has yet to develop
a clear consensus on a computational lexicon that could provide a
springboard for such methods. One of the most controversial areas has
to do with polysemy: what constitutes a clear separation into senses
of a word, and how can they be computationally characterized and
distinguished? The answer to this question is critical to breaking the
bottleneck of broad coverage semantic representation computation.

A first step towards finding an answer lies in acquiring annotated
corpora that will facilitate the use of empirical methods. The topic
of this special issue is tagging word tokens in corpora with lexical
semantic information. A concrete example of such tagging would be
specifying the sense of an ambiguous word, like {\em bank}, being used
in a particular sentence in a corpus. Lexical semantic tagging is
critical to extending reliable co-reference for information extraction
tasks, to widening the scope of responses to information retrieval
queries, to more robust dialogue understanding, and to machine
translation. In machine translation in particular, it is often
necessary to disambiguate a polysemous source word in order to
translate it correctly, since the target language may have distinct
lexical items for different senses.

We solicit articles which either:

(i) discuss the characteristics of information to be tagged and how
human tagging (hand-tagging) can be performed so as to maximize
accuracy. Such articles should concentrate on the specification of the
task and also deal with issues in providing sufficient quantities of
accurate and diverse hand-tagged data for the automatic approaches.

(ii) discuss attempts to develop automated methods and their operation
and performance. These articles should describe actual running systems
and their design and implementation.

We are particularly interested in discussions of lexical semantic
tagging methods which are part of actual applications.

Format:

In the interest of providing more coverage, we will be considering
papers that are somewhat shorter than traditional journal papers.
This would allow us to accept a maximum of 9 articles given an average
length of 10 pages.

Schedule:

November 1st, 1998 : Submission deadline
February 15th, 1999 : Notification of acceptance

Please send submissions to:

Martha Palmer
Institute for Research in Cognitive Science
400A, 3401 Walnut Street/6228
University of Pennsylvania
Philadlephia, PA 19104
Telephone: (215) 898-0361
FAX No.: (215) 573-9247
e-mail: mpalmercis.upenn.edu

 CALL FOR PAPERS
 COMPUTATIONAL LINGUISTICS
 SPECIAL ISSUE 
 ON 
 FINITE STATE METHODS IN NATURAL LANGUAGE PROCESSING


Recent years has seen a substantial increase in the use of finite
state techniques in many aspects of natural language processing as
mature tools for building large scale finite-state systems from
various research laboratories and universities become available. This
trend was by no means foreseen as late as ten years ago given the
well-known demonstration by Noam Chomsky in 1957 that finite-state
methods are inherently incapable of representing the full richness of
constructions in a natural language. Nevertheless, it is evident now
that there are many subsets of natural language that are adequately
covered by finite-state means and that there are many other areas
where finite-state approximations of more powerful formalisms are of
great practical benefit.

As a follow-up to the FSMNLP'98, International Workshop on Finite
State Methods in Natural Language Processing, it was proposed that a
collection of papers in this area be published as a special issue of
the Computational Linguistics journal. We would to encourage authors
of the papers presented at this workshop, as well as all others who
would like to contribute, to submit full versions of their papers for
consideration for this special issue.

Guest Editors: 

Lauri Karttunen (Xerox Research Centre Europe,France)
Kemal Oflazer (Bilkent University, Turkey)

Guest Editorial Board

Eric Brill (Johns Hopkins University, MD, USA) 
Eva Ejerhed (Umea University, Sweden) 
Ronald M. Kaplan (Xerox Palo Alto Research Center, CA, USA) 
Martin Kay (Xerox Palo Alto Research Center, CA, USA) 
George Kiraz (Bell Laboratories, NJ, USA) 
Andrs Kornai (BBN, MA, USA) 
Mehryar Mohri (AT&T Labs Research, NJ, USA) 
Mark-Jan Nederhof (DFKI, Germany) 
Atro Voutilainen (University of Helsinki, Finland) 


Submission Details

Please submit 6 copies of your hard-copy manuscript to

 Lauri Karttunen
 Xerox Research Centre Europe
 6 Chemin de Maupertuis
 Meylan, 38240, France

by Monday, October 19, 1998. 

The format of the submission should follow the general submission
requirements of the Journal. Manuscripts for Computational Linguistics
should be submitted on letter-size paper (8.5 by 11 inches, or A4),
double-spaced throughout, including footnotes and references. The
paper should begin with an informative abstract of approximately
150-250 words. Manuscripts must be written in English.