LINGUIST List 12.757

Mon Mar 19 2001

Calls: Finiteness, Machine Translation

Editor for this issue: Jody Huellmantel <jodylinguistlist.org>


As a matter of policy, LINGUIST discourages the use of abbreviations or acronyms in conference announcements unless they are explained in the text.

Directory

  1. Irina Nikolaeva, Finiteness
  2. Priscilla Rasmussen, Data-Driven Machine Translation (ACL-2001)

Message 1: Finiteness

Date: Sun, 18 Mar 2001 16:36:35 -0000
From: Irina Nikolaeva <i.nikolaevabtinternet.com>
Subject: Finiteness


SECOND CALL FOR PAPERS

COFERENCE ON FINITENESS

UNIVERSITY OF KONSTANZ (GERMANY), May 11-13, 2001

Though routinely employed in the morphological and syntactic analysis of 
many languages, if not all, the descriptive content and theoretical 
import of the category of finiteness is so unclear as to render it 
arbitrary and meaningless. The aim of the conference is to shed light on 
this category by focusing on questions such as these:

- Is FINITENESS an elementary notion or is it defined in terms of more 
basic notions (such as marking for tense, mood, person/number/other 
agreement, being in construction with a non-oblique subject)?

- Assuming FINITENESS is not elementary, what are the patterns of more 
basic functional categories that render such a derived category 
meaningful? (For example, are there systematic correlations between 
being marked for tense, mood, person/number/other agreement and being in 
construction with a non-oblique subject?) Are such patterns 
language-particular or are they universally predictable?

- What kinds of units can be said to be finite or non-finifte? Words or 
word forms? Constructions/clauses/sentences? If both, how is the 
FINITENESS of words related to that of constructions?

- As a word category, how does FINITENESS bear on word classes? (Is 
finite what verbs are, and non-finite what not-so-verby verbs are, with 
basic nouns and adjectives unrelated to verbs being outside the scope of 
this category altogether?)

- As a construction category, how does FINITENESS bear on construction 
classes?(Is finite what sentences and perhaps clauses are, and 
non-finite what phrases and perhaps clauses are, if desentential? 
Further, how do finite and non-finite distribute over main and 
subordinate clauses?)

- How do finite and non-finite constructions differ as domains for 
syntactic rules (e.g., binding, anaphora, case marking)? That is,what is 
the relationship between FINITENESS and syntactic opacity?

- What about FINITENESS is subject to change? (For example, can finite 
forms or constructions become non-finite, and vice versa? If so, what 
are the mechanisms of change?

For purposes of this conference the overall angle on such questions 
ought to be typological and theoretical: empirically determining 
crosslinguistic variation and its limitations ought to be taken as 
seriously as explaining what has been found, in whatever theoretical 
framework.

Invited speakers include:

Elena Kalinina, Moscow State University

Maria Koptjevskaja-Tamm, University of Stockholm

Jaklin Kornfilt, Syracuse University

David Perlmutter, University of California, San Diego

Presentation will be allotted 30 minutes with an additional 15 minutes 
for discussion. Abstract of one page should be submitted by March 30th, 
2001. If you are submitting by regular mail, abstracts should be mailed 
to:=20

Irina Nikolaeva, University of Konstanz, Fachbereich Sprachwissenschaft, 
Fach 175, Konstanz, D-78457.

If submitting electronically, please include the abstract in the body of 
the message(do not send attachments!) and send it to: 
irina.nikolaevauni-konstanz.de. Abstracts should include the author
information (author's name and affiliation, title of the paper, mailing 
address, and e-mail address). Authors are encouraged to write their 
papers, so that most of the papers to be presented in the conference 
could be published later in an edited volume.

IMPORTANT DEADLINES:

Submission deadline: March 30th, 2001

Notification of acceptance, April 10th, 2001

Conference organizers:

Irina Nikolaeva=20

irina.nikolaevauni-konstanz.de

Frans Plank

frans.plankuni-konstanz.de


Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: Data-Driven Machine Translation (ACL-2001)

Date: Mon, 19 Mar 2001 16:32:23 EST
From: Priscilla Rasmussen <rasmussecs.rutgers.edu>
Subject: Data-Driven Machine Translation (ACL-2001)


 WORKSHOP ON DATA-DRIVEN MACHINE TRANSLATION

 7 July 2001
 Toulouse, France

 http://www.cs.unca.edu/~bruce/acl01/MT.html 

- ----------------------------------------------------------------------
With the increased availability of online corpora, data-driven
approaches have become central to the NL community. A variety of
data-driven approaches have been used to help build Machine
Translation systems -- example-based, statistical MT, and other
machine learning approaches -- and there are all sorts of
possibilities for hybrid systems. We wish to bring together proponents
of as many techniques as possible to engage in a discussion of which
combinations will yield maximal success in translation.

We propose to center the workshop on Data Driven MT, by which we mean
all approaches which develop algorithms and programs to exploit data
in the development of MT, primarily the use of large bilingual corpora
created by human translators, and serving as a source of training data
for MT systems. The workshop will focus on the following topics:

- statistical machine translation (modeling, training, search)
- machine-learning in translation
- example-based machine translation
- acquisition of multilingual training data
- evaluation of data driven methods (also with rule-based methods)
- combination of various translation systems; integration of classical 
 rule-based and data driven approaches
- word/sentence alignment

An especially important question that we wish to address is which
techniques are best for each of the subparts of a complete MT system -
e.g. learning grammars, building lexicons, parsing input data,
determining transfer principles, generating target text, etc.


WORKSHOP CHAIRS

 Jessie Pinkham, Microsoft Research jessiepmicrosoft.com
 Kevin Knight, USC/ISI, knightisi.edu
 Franz Josef Och, RWTH Aachen, ochcs.rwth-aachen.de


INVITED SPEAKER

 Hermann Ney, RWTH Aachen 


PROGRAMME COMMITTEE


 Srinivas Bangalore, AT&T Research
 Ralf Brown, CMU
 Francisco Casacuberta, Polytechnic Univ. of Valencia
 Eugene Charniak, Brown University
 Ulf Hermjakob, USC/ISI
 Pierre Isabelle, Xerox Research Centre Europe
 Bob Moore, MSR
 Masaaki Nagata, NTT
 Norbert Reithinger, DFKI
 Philip Resnik, Univ. of Maryland
 Eiichiro Sumita, ATR
 Koichi Takeda, IBM Japan
 Enrique Vidal, Polytechnic Univ. of Valencia
 Stephan Vogel, Univ. of Kaiserslautern
 Hideo Watanabe, IBM TRL


SUBMISSIONS

Papers describing original work in the area of Data Driven Machine
Translation should be submitted electronically in Postscript or PDF
format to: 

 Deborah Coughlin, mailto:deborahcmicrosoft.com

Submissions should follow the two-column format of ACL proceedings and
should not exceed eight (8) pages, including references. We strongly
recommend the use of ACL LaTeX style files or Microsoft Word Style
files tailored for this year's conference. They are available from the
ACL-2001 program committee Web-site at:

 http://acl2001.dfki.de/style/ 

The paper should not include the authors' names and affiliations.
As reviewing will be blind, the submission must be associated with an
email containing the following information (ASCII text): 

 TITLE: title of the paper
 AUTHORS: list of authors
 EMAIL: email of author for correspondence
 KEYWORDS: keywords, topic sub-areas, ...
 ABSTRACT: abstract of the paper


IMPORTANT DATES

 Paper submissions 6 April 2001
 Notification of acceptance 27 April 2001 
 Camera-ready copies due 16 May 2001 
 Workshop dates 7 July 2001 


REGISTRATION

The registration fee for the workshop will be posted at a later stage.
The registration fee includes attendance of the workshop and a copy of
workshop proceedings. Follow the registration instructions at the ACL
site and indicate that you would like to attend the Data-Driven MT
workshop. 


MORE INFORMATION

 http://www.cs.unca.edu/~bruce/acl01/MT.html
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue