LINGUIST List 16.657

Sat Mar 05 2005

Calls: Comp Ling/Semitic/USA; Comp Ling/Semantics/USA

Editor for this issue: Amy Wronkowicz <>

As a matter of policy, LINGUIST discourages the use of abbreviations or acronyms in conference announcements unless they are explained in the text. To post to LINGUIST, use our convenient web form at


        1.    Mona Diab, ACL 05 Workshop on Computational Approaches to Semitic Languages
        2.    Chris Brockett, ACL 2005 Workshop: Empirical Modeling of Semantic Equivalence and Entailment

Message 1: ACL 05 Workshop on Computational Approaches to Semitic Languages

Date: 04-Mar-2005
From: Mona Diab <>
Subject: ACL 05 Workshop on Computational Approaches to Semitic Languages

Full Title: ACL 05 Workshop on Computational Approaches to Semitic Languages

Date: 29-Jun-2005 - 29-Jun-2005
Location: Ann Arbor, Michigan, United States of America
Contact Person: Mona Diab
Meeting Email:

Linguistic Field(s): Computational Linguistics

Language Family(ies): Unclassified Central Semitic

Call Deadline: 10-Apr-2005

Meeting Description:


University of Michigan, Ann Arbor
June 29, 2005

Submission Deadline April 10 2005


The Semitic family includes many languages and dialects spoken by a large number
of native speakers (around 300 Million). However, Semitic languages are still
understudied. The most prominent members of this family are Arabic and its
dialects, Hebrew, Amharic, Aramaic, Maltese and Syriac. Beyond their shared
ancestry which is apparent through pervasive cognate sharing, a common
characteristic of these languages is the rich and productive pattern-based
morphology and similar syntactic constructions.

An increasing body of computational linguistics work is starting to appear for
both Arabic and Hebrew. Arabic alone, as the largest member of the Semitic
family, has been receiving a lot of attention lately in terms of dedicated
workshops and conferences. These include, but are not limited to, the workshop
on Arabic Language Resources and Evaluation (LREC 2002), a special session on
Arabic processing in Traitement Automatique du Langage Naturel (TALN 2004), the
Workshop on Computational Approaches to Arabic Script-based Languages (COLING
2004), and the NEMLAR Arabic Language Resources and Tools Conference in Cairo,
Egypt (2004). This phenomenon has been coupled with a relative surge in
resources for Arabic due to concerted efforts by the LDC and ELDA/ELRA. However,
there is an apparent lag in the development of resources and tools for other
Semitic languages. Often, work on individual Semitic languages, unfortunately,
still tends to be done with limited awareness of ongoing research in other
Semitic languages. Within the last four years, only three workshops addressed
Semitic languages: an ACL 2002 Workshop on Computational Approaches to Semitic
Languages and an MT Summit IX Workshop on Machine Translation for Semitic
Languages in 2003, and the EAMT 2004, held in Malta, had a special session on
Semitic languages.

This workshop is a sequel to the ACL 2002 workshop and shares its goals of:

(i) heightening awareness amongst Semitic-language researchers of shared
breakthroughs and challenges,
(ii) highlighting issues common to all Semitic languages as much as possible,
(iii) encouraging the potential for developing coordinated approaches; and
(iv) in addition, leveraging resource and tool creation for less prominent
members of the Semitic language family.


We invite submissions of papers addressing any of the following issues:

- Computational approaches to phonology, morphology, syntax, semantics and
pragmatics of Semitic languages
- Applications for Semitic languages such as, but not limited to, machine
translation, summarization and information retrieval
- Tools for processing of Semitic languages (e.g. POS taggers, parsers, etc.)
- Empirical studies of unique/specific phenomena in Semitic languages
- Creating computational resources for Semitic languages
- Comparative computational studies of Semitic languages
- Leveraging resources in other languages (Semitic or other) to create resources
and tools for Semitic languages

While we invite submissions addressing any of the above topics, or related
issues, we particularly welcome work involving Semitic languages with scarce


The workshop will last for one day, June 29th, and will consist of:

- An invited talk (by Salim Roukos, IBM T. J. Watson Research Center)
- Several sessions of regular paper presentations
- A panel discussion drawing on aspects of the participating papers and their
implications for future collaboration and coordination


Submissions will consist of regular full papers of max. 8 pages, formatted
following the ACL 2005 guidelines
( All submissions must be
anonymous. Please send submissions in either .pdf or .ps form. Both submission
and review processes will be handled electronically. In a separate email with
subject SemCL05 please send names of Authors and name of contact person. We are
pursuing the possibility of publishing a selection of accepted papers in a
journal special issue on Semitic computational linguistics.


Regular paper submissions: April 10
Notification (short and regular papers): May 4
Camera-ready papers: May 15


Kareem Darwish (German University in Cairo, Egypt)
Mona Diab (Columbia University, USA)
Nizar Habash (Columbia University, USA)


For submissions, questions, comments, etc. please send email to


Ibrahim A. Alkharashi (King Abdulaziz City for Science and Technology, Saudi Arabia)
Tim Buckwalter (Linguistic Data Consortium, USA)
Violetta Cavalli-Sforza (Carnegie Mellon University, USA)
Yaacov Choueka (Bar-Ilan University, Israel)
Joseph Dichy (Lyon University, France)
Martha Evens (Illinois Institute of Technology, USA)
Ali Farghaly (SYSTRAN Software, Inc.)
Alexander Fraser (USC/ISI)
Andrew Freeman (Mitre)
Alon Itai, (Technion, Israel)
George Kiraz (Beth Mardutho: The Syriac Institute, USA)
Katrin Kirchhoff (University of Washington, USA)
Alon Lavie (Carnegie Mellon University, USA)
Mohamed Maamouri (Linguistic Data Consortium, USA)
Uzzi Ornan (Technion, Israel)
Anne De Roeck (Open University, UK)
Michael Rosner (University of Malta, Malta)
Salim Roukos (IBM, USA)
Khalil Sima'an (University of Amsterdam, Netherlands)
Abdelhadi Soudi (ENIM, Rabat, Morocco)
Shuly Wintner (University of Haifa, Israel)
Remi Zajac (SYSTRAN Software, USA)

Message 2: ACL 2005 Workshop: Empirical Modeling of Semantic Equivalence and Entailment

Date: 04-Mar-2005
From: Chris Brockett <>
Subject: ACL 2005 Workshop: Empirical Modeling of Semantic Equivalence and Entailment

Full Title: ACL 2005 Workshop: Empirical Modeling of Semantic Equivalence and

Date: 30-Jun-2005 - 30-Jun-2005
Location: Ann Arbor, MI, United States of America
Contact Person: Bill Dolan
Meeting Email:
Web Site:

Linguistic Field(s): Computational Linguistics; Pragmatics; Semantics

Call Deadline: 20-Apr-2005

Meeting Description:


Workshop at the Annual Meeting of the Association of Computational Linguistics
(ACL 2005)

Ann Arbor, Michigan
June 30, 2005

Submission Deadline: April 20, 2005

Many natural language processing applications require the ability to recognize
when two text segments - however superficially distinct – overlap semantically.
Question-Answering (QA), Information Extraction (IE), command-and-control, and
multi-document summarization are examples of applications that need precise
information about the relationship between different text segments. The concepts
of entailment and paraphrase are useful in characterizing these relationships.
For instance, does the meaning of one text entail all or part of the other, as
in the following example?

I bought a science fiction novel
I bought a book

Or are the two texts so close in meaning that they can be considered
paraphrases, linked by many bidirectional entailments?

On its way to an extended mission at Saturn, the Cassini probe on Friday
makes its closest rendezvous with Saturn's dark moon Phoebe.
The Cassini spacecraft, which is en route to Saturn, is about to make a
close pass of the ringed planet's mysterious moon Phoebe

Quantifying semantic overlap is a fundamental challenge that encompasses issues
of lexical choice, syntactic alternation, and reference/discourse structure. The
last few years have seen a surge in interest in modeling techniques aimed at
measuring semantic equivalence and entailment, with work on paraphrase
acquisition/generation, WordNet-based expansion, distributional similarity,
supervised learning of semantic variability in information extraction, and the
identification of patterns in template-based QA. While different applications
face similar underlying semantic problems, these problems are typically
addressed in an application-specific manner. In the absence of a generic
evaluation framework, it is difficult to compare semantic methods that were
developed for different applications. One key goal of this workshop will be to
stimulate discussion around the issue of developing common datasets and
evaluation strategies

More generally, our aim is to bring together people working on empirical,
application-independent approaches to the practical problems of semantic
inference. We welcome papers describing original work on computational
approaches to modeling the problems of semantic equivalence and entailment, and
encourage submissions on the following (non-exclusive) topics:

-- Probabilistic modeling of meaning equivalence/entailment between arbitrary
text segments
-- Methods for generating textual entailments/paraphrases from novel inputs
-- String-based vs. linguistically-informed approaches to measuring meaning overlap
-- Developing training/test corpora: novel sources of data and strategies for
automating data collection
-- Human inter-annotator agreement on annotation tasks: Can humans reliably tag
the kinds of inferences that are needed for real applications? What information
can humans reliably tag?
-- Automated evaluation metrics for meaning equivalence/paraphrase
-- Empirical investigations into the types of entailment/equivalence inferences
needed for particular applications
-- Methods for determining which of many entailments between two text segments
are relevant for specific applications
-- Modeling lexical-level entailment relationships which are geared to be part
of entailment modeling for larger texts (as opposed to more general measures of
-- Specific applications that exploit general measures of semantic overlap
-- Extension of MT techniques to problems of monolingual semantic
equivalence/entailment relationships

The workshop will be anchored by two panel discussions, the first exploring how
the problem of semantic overlap has been successfully handled in several
applications (question answer, information retrieval, etc.) and the second aimed
at developing a shared evaluation task focused on this problem.


Paper submission deadline: April 20, 2005
Camera ready copy: May 20, 2005
Workshop date: June 30, 2005


Submissions will consist of regular full papers of max. 6 pages, formatted
following the ACL 2005 guidelines..
Both submission and review processes will be handled electronically.


Two datasets are being released in conjunction with this workshop, in order to
stimulate submissions and thinking around this topic. While we hope that these
will be useful for training, evaluation, and analysis, authors are invited to
use whatever resources/approaches are at their disposal.

-- The Pascal Recognising Textual Entailment Challenge Corpus: 1K sentence pairs
that have been human-annotated with directional entailments
-- The Microsoft Research Paraphrase Corpus: 5801 likely sentential paraphrase
pairs gathered automatically from topically clustered news articles. Multiple
human raters examined each pair, classifying more than 3900 as close enough in
meaning to be considered equivalent
( This is the first time this
corpus has been made available.


Bill Dolan (Microsoft Research)
Ido Dagan (Bar Ilan University)


For questions, comments, etc. please send email to


Srinivas Bangalore (AT&T Research)
Regina Barzilay (MIT)
Chris Brockett (Microsoft Research)
Pascale Fung (Hong Kong University of Science and Technology)
Oren Glickman (Bar Ilan University)
Cyril Goutte (Xerox Research Centre Europe)
Ed Hovy (ISI)
Kentaro Inui (Nara Institute of Science and Technology)
Dekang Lin (University of Alberta)
Daniel Marcu (ISI)
Kathy McKeown (Columbia University)
Dan Moldovan (University of Texas at Dallas)
Chris Quirk (Microsoft Research)
Maarten de Rijke (University of Amsterdam)
Hinrich Schuetze (University of Stuttgart)
Satoshi Sekine (New York University)
Peter Turney (National Research Council of Canada)

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