LINGUIST List 10.943

Thu Jun 17 1999

Calls: Parsing, Multimedia Indexing and Retrieval

Editor for this issue: Scott Fults <>

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


  1. Harry Bunt, IWPT'99 CHANGE OF DATES !!
  2. Zhongfei Zhang, ACM SIGIR Multimedia Indexing and Retrieval Workshop

Message 1: IWPT'99 CHANGE OF DATES !!

Date: Thu, 17 Jun 1999 23:03:47 +0200
From: Harry Bunt <>

In view of the closeness of the original dates (December 20-22, 1999) to 
the millenium change, which may cause inconveniencies, the dates of IWPT'99 
have changed to February 23-25, 2000. IWPT'99 thus becomes IWPT 2000. 
Below is the updated Call for papers, with revised time table.
- -------------------------------------------------------------------------

 C a l l f o r P a p e r s 

 IWPT 2000 

 6th International Workshop on Parsing Technologies

 Sponsored by ACL/SIGPARSE

 23-25 February, 2000
 Trento, Italy

The ITC-IRST (Institute for Scientific and Technological Research) 
in Trento, in the North of Italy, will host the 6th International 
Workshop on Parsing Technologies (IWPT 2000) from 23 to 25 February, 

IWPT 2000 continues the tradition of biennial workshops on parsing 
technology organised by SIGPARSE, the Special Interest Group on
Parsing of the Association for Computational Linguistics (ACL). 
This workshop series was initiated by Masaru Tomita in 1989. 
The first workshop, in Pittsburgh and Hidden Valley, was followed 
by workshops in Cancun (Mexico) in 1991; Tilburg (Netherlands) and 
Durbuy (Belgium) in 1993; Prague and Karlovy Vary (Czech Republic) 
in 1995; and Boston/Cambridge (Massachusetts) in 1997. 

More information can be found on the IWPT 2000 home page at: 

 < >

Topics of interest for IWPT 2000
- ------------------------------
Theoretical and practical studies of parsing algorithms for natural 
language sentences, texts, fragments, dialogues, ill-formed sentences, 
speech input, multi-dimensional (pictorial) language, and parsing issues 
arising or viewed in a multimodal context. Both grammar-based and 
statistical approaches are welcome.

Submitting Papers
- ---------------
Prospective authors are invited to send full papers to the IWPT 2000 
programme chairman John Carroll. Papers must be in the format given 
at the IWPT 2000 home pages (see below). Papers should not exceed 12 
pages. Submission is electronically, in postscript form. 
Send papers to:

All submitted papers will be reviewed by the programme committee. 

Deadline for paper submission	: November 5, 1999
Notification of acceptance	: December 3, 1999
Final papers due		: January 7, 2000

In addition to the papers that will be accepted for full length 
presentation, papers may be accepted for poster presentations 
(two pages in the proceedings).

Instruction for authors
- ---------------------
Instructions for authors can be found at URL:
< >
or can be obtained from the programme chairman.

Programme Committee
- -----------------
Robert Berwick (MIT, Cambridge, USA)
Harry Bunt (Tilburg University, Netherlands)
Bob Carpenter (Bell Labs, Murray Hill, USA)
John Carroll (University of Sussex, Brighton, UK) (chair) 
Ken Church (Bell Labs, Murray Hill, USA)
Mark Johnson (Brown University, Providence, USA)
Aravind Joshi (University of Pennsylvania, Philadelphia, USA)
Ronald Kaplan (Xerox, Palo Alto, USA)
Martin Kay (Xerox, Palo Alto, USA)
Bernard Lang (INRIA, Paris, France)
Alon Lavie (Carnegie-Mellon University, Pittsburgh, USA)
Anton Nijholt (University of Twente, Enschede, Netherlands)
Christer Samuelsson (Xerox Grenoble, France)
Mark Steedman (University of Edinburgh, UK)
Oliviero Stock (IRST, Trento, Italy)
Hozumi Tanaka (Tokyo Institute of Technology, Japan)
Masaru Tomita (Stanford University, USA)
Hans Uszkoreit (DFKI, Saarbruecken, Germany)
K. Vijay-Shanker (University of Delaware, Newark, USA)
David Weir (University of Sussex, Brighton, UK)
Mats Wiren (Telia Research, Stockholm, Sweden)

- ----------
General Chair: Harry Bunt (Tilburg University, Netherlands) 
Programme Chair: John Carroll (University of Sussex, UK) 
Local Arrangements Chair: Alberto Lavelli (IRST, Trento, Italy)

- -------
SIGPARSE, Special Interest Group on Parsing of the Association for 
 Computational Linguistics
AI*IA, Italian Association for Artificial Intelligence

Further information
- -----------------
Information about IWPT 2000 can be found at the URL:

 < >

At this site you can also obtain information about previous IWPTs, 
proceedings and SIGPARSE related activities.
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: ACM SIGIR Multimedia Indexing and Retrieval Workshop

Date: Thu, 17 Jun 1999 10:35:04 -0400 (EDT)
From: Zhongfei Zhang <zhongfeicedar.Buffalo.EDU>
Subject: ACM SIGIR Multimedia Indexing and Retrieval Workshop

Note that the paper/statement of interest submission deadline
has been extended to June 25th, 1999.

Thanks for attention.

Zhongfei Zhang
SUNY Buffalo

- ---------------------------------------------------------

 ACM SIGIR'99 Post-Conference Workshop on
 Multimedia Indexing and Retrieval
 (SIGIR -- Special Interest Group on Information Retrieval)
 Berkeley, CA, August 19, 1999

 Call For Participation


- --------

This workshop is a follow-up to last year's very successful workshop on the
same topic. Since the field is advancing so rapidly, it was felt that an
annual workshop would be worthwhile. 

The focus is on the required functionality, techniques, and evaluation
criteria for multimedia information retrieval systems. Researchers
have been investigating content-based retrieval from non-text sources
such as images, audio and video. Initially, the focus of these efforts
were on content analysis and retrieval techniques tailored to a
specific media; more recently, researchers have started to combine
attributes from various media. The goal of multimedia IR systems is to
handle general queries such as "find outdoor pictures or video of
Clinton and Gore discussing environmental issues". Answering such
queries requires intelligent exploitation of both text/speech and
visual content. Multimedia IR is a very broad area covering both
infrastructure issues (e.g. efficient storage criteria, networking,
client-server models) and intelligent content analysis and retrieval.
Since this is a one-day workshop, we have chosen three focus areas in
the intelligent analysis and retrieval area.

About the workshop
- ----------------

The first focus of this workshop is on integrating information from
various media sources in order to handle multimodal queries on large,
diverse databases. An example of such a collection would be the
WWW. In such cases, a query may be decomposed into a set of media
queries, each involving a different indexing scheme. The interaction
of various media sources that occur in the same context (e.g., text
accompanying pictures, audio accompanying video) is of special
interest; such interaction can be exploited in both the content
analysis and retrieval phases.

The second focus deals with examples of research using content and
organization of multimedia information into semantic classes. Users
pose and expect a retrieval to provide answers to semantic
questions. In practice this is difficult to achieve. Building
structures that encode semantic information in a fairly domain
independent and robust manner is extremely difficult. A quick review
of computer vision research over the last few years points to this
difficulty. In many cases, image content can be used in conjunction
with user interaction and domain specificity to retrieve semantically
meaningful information. However, it is clear that retrieval by
similarity of visual attributes when used arbitrarily cannot provide
semantically meaningful information. For example, a search for a red
flower by color red on a very heterogeneous database cannot be
expected to yield meaningful results. On the other hand retrieval of
red flowers in a database of flowers can be achieved using color. In
context therefore, examples of research using content and organization
of multimedia information into semantic classes will be discussed.

Many systems, particularly image and video based ones require an
example picture which can be used as a query (alternatively, the user
may be required to draw a picture). It may be unrealistic to expect an
example image to be always available. Thus, it would be useful to find
ways of generating new queries. Can NLP techniques be combined with
computer vision techniques to generate such queries? Or can multimodal
retrieval techniques be combined to create queries suitable for image,
video and audio retrieval? In general, a question is how can we
create realistic queries for realistic systems.

The third focus of this workshop is on evaluation techniques for
multimedia retrieval. Currently, most researchers are using the
standard evaluation measures defined for text documents; these need to
be extended/modified for multimedia documents. There is also a high
degree of subjectivity involved that needs to be addressed.

Finally, we will also devote one session to discussing MPEG-7
standards and content. By the time of the workshop, the selection
committee would have made their choices for standards.

We will focus on the following specific topics: 

 - content analysis and retrieval from various media (text, images, video,
 - interaction of modalities (e.g. text, images) in indexing, retrieval 
 - effective user interfaces (permitting query refinement etc.) 
 - evaluation methodologies for multimedia information. We have found that
 researchers pay insufficient attention to it. 
 - techniques for relevance ranking 
 - multimodal query formation/decomposition 
 - logic formalisms for multimodal queries 
 - indexing and retrieval from scanned documents - e.g extracting text from
 images, word spotting - as a retrieval technique for both handwritten and
 printed documents. 
 - testbeds for evaluating multimodal retrieval: it would be nice to have
 some resource sharing here since annotating these, and coming up with a
 good query set are difficult 

- -----------

Two types of participation are expected. Those interested in making a
presentation at this workshop should submit their full papers either
in online postscript version or in hardcopy by regular mail to the
address given below. The papers should not exceed 5,000 words,
including figures, tables, and references. Those interested in
participating, but not presenting papers, should submit a statement of
interest, not to exceed 500 words. This should clearly state what
aspect(s) of the workshop reflect their research interest. These will
be used to select panelists. Both types of submissions are due on
Friday, June 25th. Decisions will be made no later than Friday, July
2nd. In the case of paper submission, the final camera-ready papers
are due on July 23rd. Working notes will be made available to all
participants at the workshop. All the submissions should be sent to:

Dr. Rohini K. Srihari 
CEDAR/SUNY at Buffalo 
UB Commons 
520 Lee Entrance, Suite 202 
Amherst, NY 14228 - 2583 
Phone: (716) 645-6164 ext. 102 Fax: (716) 645-6176 

- ----------

Workshop chairs (also program chairs): 

 Rohini K. Srihari 
 CEDAR, SUNY at Buffalo 
 Amherst, NY 14228 - 2583 
 Zhongfei Zhang 
 CEDAR, SUNY at Buffalo 
 Amherst, NY 14228 - 2583 
 R. Manmatha 
 Computer Science Dept., Univ. of Massachusetts 
 Amherst, MA 01003 
 S. Ravela 
 Computer Science Dept., Univ. of Massachusetts 
 Amherst, MA 01003 

- -------

 Paper or statement of interest submission: 
 June 25th, 1999. 
 July 2nd, 1999. 
 Camera-Ready Paper Due: 
 July 23rd, 1999 
 SIGIR Conference: 
 August 15 - 19, 1999 
 Workshop Date: 
 to be announced. 

Further information
- -----------------

Further questions may be directed to the address above, or go to the Web
page of this workshop at

or the SIGIR Conference main Web Page at
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue