[Indic-computing-users] [ICON-2002]: LATEST CALL FOR PARTICIPATION (fwd)
Status: Alpha
Brought to you by:
jkoshy
Menu
▾
▴
[Indic-computing-users] [ICON-2002]: LATEST CALL FOR PARTICIPATION (fwd)
|
From: Frederick N. <fr...@by...> - 2002-12-10 19:07:47
|
---------- Forwarded message ----------
LATEST CALL FOR PARTICIPATION=20
ICON-2002: INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING
Mumbai, India
December 18-21, 2002
http://www.iiit.net/conferences/icon2002.html
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
IMPORTANT DATES:
=20
PRE-CONFERENCE TUTORIALS : December 18, 2002
=20
CONFERENCE : December 19-21, 2002
=20
VENUE : National Centre Software Technology=20
Raintree Marg, Opp. Kharghar Railway Statio=
n,
Sector 7, CBD Belapur,
Navi Mumbai - 400614, India.
(Please visit http://www.ncst.ernet.in/kbcs=
2002)
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
UPDATE:=20
* LOW COST HOSTEL ACCOMMODATION IS AVAILABLE=20
* EXTENSION OF DEADLINE
for seeking financial support : December 10, 2002
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
The International Conference on Natural Language Processing(ICON)
will be held in Mumbai, India during December 18-21, 2002. The
conference is intended to act as a forum for promoting interaction
among researchers in the field of Natural Language Processing in India
and abroad. The conference will be preceded by a day of pre-conference
tutorials on December 18, 2002. The conference is being held
concurrently with KBCS-2002: International Conference on Knowledge
Based Computer Systems.
Outline
=20
1. Technical Programme
2. Special session on Linguistics & Natural Language Processin=
g
3. Panel discussion: Role of Linguists in Building NLP Systems
4. Keynote address abstract
5. Invited talk abstract
6. Pre-Conference tutorials =20
7. Registration details =20
=20
*************************************************************************
TECHNICAL PROGRAMME=20
*************************************************************************
KEYNOTE ADDRESS
=20
Starting with Complex Primitives Pays Off: Complicate Locally, Simplify
Globally
Prof. Aravind K Joshi, University of Pennsylvania
INVITED PAPER
=20
NLP, Information-mining and the New Global Village
Prof. Benjamin Tsou, City University of Hong Kong
MORPHOLOGY
=20
Morphological Analyzer for Tamil
P Anandan, K. Saravanan, Ranjani Parthasarathi and T.V.Geetha
=20
Morphological Parsing Using Ample, SenTrans, and PC-PATR
Robert D. Eaton
=20
Improved Porter's Algorithm for Root Word Stemming
M Saravanan, P.C. Reghu Raj, Vadali Srinivasa Murty and S.Raman
=20
Classification of Words Based on Affix Evidence
Utpal Sharma, Jugal Kalita and Rajib Das
=20
=20
PARSING
=20
A Constraint Based Parser Using Integer Programming
Akshar Bharati, Rajeev Sangal and T. Papi Reddy
=20
SProUT - Shallow Processing with Unification and Typed Feature Structures
Markus Becker, Witold Drozdzynski, Hans-Ulrich Krieger, Jakub Piskorski, =
Ulrich Schafer
and Feiyu Xu
=20
Treebank Development: the TUT Approach
Leonardo Lesmo, Vincenzo Lombardo and Cristina Bosco
=20
A TAG Approach to Basic Clause Patterns in Oriya
Rajat Kumar Mohanty
=20
A Dependency Parser for Hindi
Mark Pedersen
=20
Saarthaka: A Generalized HPSG Parser for English and Hindi
D Sharma, K Vikram, Manav R Mital, A Mukerjee and A M Raina
=20
=20
STATISTICAL LANGUAGE MODELS
=20
Readability Modelling Using Statistical Regression- a Study on Bangla Text=
s
Sreerupa Das and B.B.Chaudhuri
=20
Statistical Language Modeling Using Latent Syntactic-Semantic Analysis
Dharmendra Kanejiya, Arun Kumar and Surendra Prasad
=20
Basic Statistical Analysis of Corpus and Cross Comparison among Corpora
Prakash Rao K, Akshar Bharati, Rajeev Sangal and S.M.Bendre
=20
=20
LEXICAL RESOURCES
=20
Electronic Thesaurus for Tamil
S Rajendran=20
=20
Automatic Generation of Concept Dictionary from a Document
Nitin Verma and Pushpak Bhattacharyya
=20
=20
MACHINE TRANSLATION
=20
An Algorithm for Aligning Sentences in Bilingual Corpora Using Lexical In=
formation
Akshar Bharati, Sriram V, Vamshi Krishna A, Rajeev Sangal and S.M. Bend=
re
=20
=20
SEMANTICS=20
=20
Evaluating the WASPBENCH, a Lexicography Tool Incorporating Word Sense Di=
sambiguation
Rob Koeling and Adam Kilgarriff
=20
Applying Semantic Classes in Event Detection and Tracking
Juha Makkonen, Helena Ahonen-Myka and Marko Salmenkivi
=20
Using Verb-Noun Association for Word Sense Disambiguation
Dipak Kumar Narayan, Pushpak Bhattacharyya
=20
Using Semantic Representations in Question Answering
Sameer S. Pradhan, Valerie Krugler, Wayne Ward, Dan Jurafsky and James H. =
Martin
=20
=20
INFORMATION EXTRACTION AND RETRIEVAL
=20
A Document Space Model for Automated Text Classification based on Frequenc=
y Distribution Across Categories
Akshar Bharati, Kiran Varanasi, Chaitanya Kamisetty, Rajeev Sangal and S.M=
=2EBendre
=20
Knowledge Extraction from Indo-Aryan Family of Natural Languages Using a =
Rule Based Approach
Kuntal Dey, Sunil Kumar Dubey, Avinash Ghalke and Pushpak Bhattacharyya
=20
Phrase Grammar for Precision Content Retrieval
P.C. Reghu Raj and S. Raman
=20
=20
DIALOGUE
=20
Modelling Dialogue Systems by Finite Automata
Ivan Kopecek and Libor Skarvada
=20
A Dialogue Manager for Semantic Web Documents
Paulo Quaresma and Irene Pimenta Rodrigues
=20
=20
FONT, KEY BOARD
=20
Indian Languag Support for X-Window System
Anitha Nalluri, Bala Saraswathi A., Bharathi S., Hema A. Murthy,=20
Patricia J., Ranbir Singh S., Timothy A. Gonsalves, Vidhya M.S. and Viveka=
Nathan K.
=20
Finite State Transliteration of South Asian Text Encodings
John C. Paolillo
=20
=20
OCR
=20
LEKHAK: A system for Online Recognition of Handwritten Tamil Characters
B.J. Manikandan, Gowri Shankar, V.Anoop, A.Datta and V.S.Chakravarthy
=20
=20
SPEECH
=20
Speech Database for Indian Languages- A Preliminary Study
A.Nayeemulla Khan, Suryakanth V. Gangashetty, and S. Rajenderan
=20
Building Hindi and Telugu Voices using Festvox
S.P. Kishore, Rajeev Sangal and M. Srinivas
=20
A Data-Driven Synthesis Approach For Indian Languages using Syllable as Ba=
sic Unit
S.P. Kishore, Rohit Kumar, and Rajeev Sangal
=20
Text-To-Speech (TTS) in Indian Languages
N. Sridhar Krishna, Hema A. Murthy and Timothy A.Gonsalves
=20
Language Identification Using Spectral Vector Distribution Across the Lang=
uages
T.Nagarajan and Hema A. Murthy
*********************************************************************
SPECIAL SESSION ON 19 DECEMBER 2002
*********************************************************************
LINGUISTICS AND NATURAL LANGUAGE PROCESSING
=20
Transfer Grammar Rules: The case of relative clause construction in Englis=
h,=20
Hindi and Tamil
B.Lakshmi Bai=20
=09
Indian Languages and the Future of Information Technology
Durgesh Rao =20
=20
An online E-dictionary of idioms (Muhavara) and proverbs (Lokokti) and Tea=
cher=20
controlled Expert System
Pramod K Sharma=20
=20
The Preparation of Typological Grammars: The Need of the Hour
K.V.Subbarao=20
=20
**********************************************************************
PANEL DISCUSSION ON 20 DECEMBER 2002
**********************************************************************
Role of Linguists in Building Natural Language Processing Systems
Moderator: Prof Aravind K Joshi, University of Pennsylvania
Panel: Shivaji Bandopadhyaya; Pushpak Bhattacharya;
Tanmoy Bhattacharya; Achla Misri Raina; U.N Singh=20
=20
**************************************************************************=
*****
KEYNOTE ADDRESS ABSTRACT
**************************************************************************=
*****
Starting with Complex Primitives Pays Off: Complicate Locally, Simplify=
=20
Globally
Prof. Aravind K Joshi, University of Pennsylvania
ABSTRACT
In setting up a formal system to specify a grammar formalism,=20
the conventional (mathematical) wisdom is to start with
primitives (basic primitive structures) as simple as possible and then
introduce various operations for constructing more complex structures. An
alternate approach is to start with complex (more complicated)
primitives, which directly capture some crucial linguistic properties
and then introduce some general operations for composing these complex
structures. These two approaches provide different domains of locality,
i.e., domain over which various types of linguistic dependencies can be
specified. This latter approach, characterized as Complicate Locally,
Simplify Globally (CLSG), pushes non-local dependencies to become local,
i.e., they arise in the basic primitive structures to start with. Although
my talk will concern primarily with natural language processing, it is
expected that this approach will productive in other domains of AI.
=20
The CLSG approach has led to some new insights into syntactic description,
semantic composition, language generation, statistical processing, and
psycholinguistic properties, all these with possible relevance to the
cognitive architecture for language. I will describe these results in
an introductory manner. I will also briefly talk about the implications
of this approach for the characterization of discourse structure.=20
=20
Towards the end of my talk I will briefly discuss the applications of
this approach to the description of secondary and higher structures
(folded structures) of some biological sequences.
=20
**************************************************************************=
*****
INVITED TALK ABSTRACT=20
**************************************************************************=
*****
NLP, Information-mining and the New Global Village
Prof. Benjamin Tsou, City University of Hong Kong
ABSTRACT
Rapid Cyber Age developments within the Global Village have necessitate=
d=20
much more sophisticated efforts in information extraction and mining than=
=20
hitherto attempted or contemplated. This is because the identification of
new words or unknown words, especially proper nouns or named entities,=20
constitutes an increasingly pressing major challenge for any on-line NLP=
=20
system, ranging from word segmentation to search engine construction. As=
=20
civilization develops and Man moves forward, new cultural and physical=20
artifacts are =93necessarily named=94 ala Kripke, as salient aspects of th=
e=20
concomitant information growth gain differential importance. =20
=20
What is the extent and nature of these new named entities? How and=20
why do they come about? Why do older named entities dissipate? What=20
constraints could there be on net gain or loss - and, most importantly,=
=20
what may be their broader and practical impact on natural language process=
ing? =20
These new questions, not yet posed in onomastics, are timely and important=
ones=20
for information mining. =20
=20
The general, balanced, or specialized corpora, as traditionally unders=
tood,=20
are seen to offer unnecessary but inherent limitations on what information=
may=20
be mined from them and fully utilized. The idea of synchronous corpus is=
=20
introduced and exemplified through LIVAC, a 100 million character Chinese =
corpus=20
drawn from different Chinese communities. A WINDOWS approach is taken to=
=20
explore the phenomenal growth and attrition of named entities in language,=
as=20
well as the actuation and realization of lexical innovation across space=
=20
(different communities) and time (different years), and the possible under=
lying
regularities. =20
=20
Word entropy is explored as an important step towards validating=20
the creation of intermediate dynamic repertoire and database especially us=
eful for
large scale unsupervised learning in future hybrid approach.
**************************************************************************=
*****
PRE-CONFERENCE TUTORIALS
**************************************************************************=
*****
The conference will feature 4 half day tutorials,on December 18, 2002. =
=20
=20
1 (pre-noon): Automatic Text Summarization - Dr. Inderjeet Mani
=20
2 (pre-noon): Introduction to Computational Linguistics - Dr. Dipti Sharma
and Mrs. Amba Kulkarni
3 (afternoon): How to sketch words - Dr. Adam Kilgarriff
=20
4 (afternoon): Interlingua Based Information Processing in the
Context of Indian Languages - Dr. Pushpak Bhattacharya
=20
TUTORIAL ABSTRACTS=20
=20
1. Automatic Text Summarization
Dr Inderjeet Mani, The MITRE Corporation, USA
=20
With the explosion in the quantity of on-line text and
multimedia information in recent years, demand for automatic text
summarization technology is growing. The goal of automatic text
summarization is to take a source document or documents, extract
information content from it, and present the most important content in a
condensed form in a manner sensitive to the needs of the user and task. In
this tutorial, I will provide an overview of the latest developments
in automatic summarization, including methods for producing extracts
and abstracts, evaluation strategies, and new problem and application
areas. Human abstracting, and linguistic and statistical methods will be
described, with an emphasis on empirical results. Recent evaluations such
as SUMMAC, the Document Understanding Conference, and the Japanese Text
Summarization Challenge will be discussed. Links to relevant resources,
including bibliographies, will be provided. The goal of this half-day
tutorial is to familiarize participants with the state of the art in
automated text summarization and to give them a perspective on the current
research frontier in this area. The expected audience of the proposed
tutorial includes researchers, graduate students in Natural Language
Processing, Information Retrieval, and Artificial Intelligence, software
developers, and research managers. A general background in information
retrieval and/or natural language processing is desirable, and familiarity
with computer science and artificial intelligence is required.
=20
=20
2. Introduction to Computational Linguistics
Dr Dipti Misra Sharma & Mrs Amba P Kulkarni, International Institute
of Information Technology, Hyderabad
=20
Applications such as machine translation requires
that linguists participate actively in their development.
Language resources are a primary need for any
type of language processing. Resources, whether they are
bi-/Mono-lingual Dictionaries or grammars with precise
rules for computer applications need experts' knowledge.
Linguists play a crucial role in the development
of these resources. However, analysing large amount of
data and coming to generalizations can be a laborious task.
Technology can now help in gathering and grouping the data for
analyses. The data is not only useful for the linguists
for drawing generalizations but it also presents aspects of
language which offer insight in the theory building.
=20
The tutorial aims at familiarising linguists with the tools
and resources available for various computer applications
such as machine translation, information extraction etc.
=20
=20
3. How to sketch words
Dr Adam Kilgariff, ITRI, University of Brighton, Brighton, UK
=20
Since the advent of computerised corpora in linguistics (computational
or otherwise), the Key Word In Context (KWIC) concordance has been the
basic corpus linguist's tool. It allows the researchers to efficiently
view the evidence of how the word behaves. Various well-designed
interfaces, with flexible sorting criteria and support for
sophisticated searches, have been developed (eg WordSmith, Xkwic).
=20
The limitations of KWIC become apparent for large corpora and common
words: there is too much data to get a good overview of the word's
behaviour by simply looking at a sample of instances.
=20
Church and Hanks (1989) introduced the Mutual Infomation statistic to
summarise the data, for cases where there was too much to read it all,
and so that high-salience patterns were brought to the researcher's
attention. This (and other statistics offered since) have offered
improved access to the information implicit in the corpus. However,
the statistics have not been ideal, and the lists have thrown together
items taking different grammatical roles in relation to the word being
investigated. Thus the same list will include a verb's subjects,
objects, modifiers, and other material which has frequently been found
in the vicinity of the keyword but does not stand in any
linguistically significant relation to it.
=20
Word sketches are a response to these shortcomings. They provide a
list of statistically salient collocations for each grammatical
relation (and use an improved salience statistic). They provide an
easily-readable account of a word's grammatical and collocational
behaviour, suitable for students of the language, lexicographers, and
the language technologist who needs to understand the behaviour of the
words that are critical to an application.
=20
4. Interlingua Based Information Processing in the Context of Indian
Languages
Dr Pushpak Bhattacharyya, Indian Institute of Technology, Bombay
=20
India is a land of multiple languages and dialects. It is
necessary to enable these systems of communication onto=20
the internet and cross the language Barrier even among the=20
local languages. Though Hindi is the natioanl language of=20
the country, there are other very important languages like=20
Bengali, Marathi, Tamil and so on which are spoken by
numerous people not only within the counry, but overseas also.
=20
In this talk, we describe our work on the use of a recently=20
proposed interlingua called the Universal Networking Language=20
(UNL) in the context of Indian Languages. UNL is a medium of=20
information exchange and transfer on the web in the natural=20
languages of the world. 12 languages of the world have been=20
linked through the UNL by means analysers and generators.
We have been working on the analysers and generators for=20
English, Hindi, Marathi and Bengali. Also we are doing theoretical=20
studies on this multilinguality framework. Finally, all this=20
effort requires rich lexical resources like wordnets and semantically=20
enriched dictionaries. The talk will also touch upon our effort=20
at building the Indo Wordnet.
**********************************************************************
REGISTRATION DETAILS
**********************************************************************
IMPORTANT DATES:
=20
Pre-Conference Tutorials : December 18, 2002
=20
Conference : December 19-21, 2002
=20
Registration deadline : December 12, 2002
(After December 12, 2002=20
on site registration only)
=20
EXTENSION OF DEADLINE
for seeking financial support : December 10, 2002
=20
* LOW COST HOSTEL ACCOMMODATION IS AVAILABLE *
ACCOMMODATION DETAILS: Please visit http://www.ncst.ernet.in/kbcs2002=
=20
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
REGISTRATION FEE=20
=20
MAIN CONFERENCE
=20
Delegates from Non-profit Rs. 2000
& Educational Organisations (US$ 50)=20
=20
Other Delegates Rs. 3000
(US$ 70)=20
=20
Full time bona-fide students Rs. 950=20
from Indian academic institutes
(Limited number of slots only)
=20
=20
PRE-CONFERENCE TUTORIALS (Half Day) =20
Registration charges for each tutorial =20
=20
Delegates from Non-profit Rs. 1000
& Educational Organisations (US$ 25)=20
=20
Other Delegates Rs. 1200
(US$ 30)=20
=20
Full time bona-fide students Rs. 500=20
from Indian academic institutes
(Limited number of slots only)
=20
=20
* The students must produce a certificate from the Head/Director of the=
ir=20
respective institutes/Colleges regarding their full-time bona-fide=20
status to avail special student registration. The conference registra=
tion
fee for students does not include the copy of the proceedings.
=20
* Limited funds are available to support travel and stay of faculty and=
=20
students. Special funds are available to support travel and stay of
faculty and students of linguistics, including registration fees.
=20
* For financial support send the registration form along with the appli=
cation
for support giving details of your educational qualifications, percen=
tage
of marks and past & ongoing activities. They may be sent by email to
ico...@ii... or by post to ICON-2002 Secretariat.
=20
=20
Encl: ICON-2002: REGISTRATION FORM
**************************************************************************=
****
ICON-2002 =20
International Conference On
Natural Language Processing
December 18 - 21, 2002, Mumbai
=20
=20
REGISTRATION FORM
=20
=20
Last Name/Surname: ________________First Name: ________________________
Address: _______________________________________________________________
___________________________________________________________=
____
City: ____________________________State:_______________________________
Country: ____________________________Pincode:_____________________________
Affiliation: _____________________________________________________________=
__
Phone (O): _______________________________(R):____________________________=
_
Fax: _____________________________Email:_____________________________
=20
Total registration amount: ____________________________
Cheque/Bank draft No. _______________________ Bank ___________________=
_
=20
CONFERENCE REGISTRATION:
=20
[ ]=09Delegates from not-for-profit R&D : INR 2000, US$ 50
and Educational Institutions
=20
[ ]=09Others Delegates=09 : INR 3000, US$ 70
=20
[ ]=09Full time bona-fide student from Indian : INR 950
academic institutions
=20
PRE-CONFERENCE TUTORIALS ON DECEMBER 18, 2002
=20
Registration fee for each half-day tutorial is as follows.
[ ]=09Delegates from not-for-profit R&D=09 : INR 800, US$ 20
and Educational Institutions=20
[ ]=09Others Delegates=09=09=09 : INR 1200, US$ 30
[ ] Full time bona-fide students from Indian : INR 500 =20
academic institutions=20
=20
Please select the tutorials you would like to attend:=20
=20
[ ] Tutorial 1: Automatic Text Summarization
[ ] Tutorial 2: Introduction to Computational Linguistics
[ ] Tutorial 3: How to sketch words
[ ] Tutorial 4: Interlingua Based Information Processing in the Context =
of =20
Indian Languages
=20
NOTE:
- All tutorials are half day. =20
- Tutorials 1 & 2 will be held in parallel sessions in the morning.
- Tutorials 3 & 4 will be held in parallel sessions in the evening.
- Avoid time clashes while selecting the tutorials
=20
CANCELLATION/REFUND POLICY: There will be no cancellation fee till=20
December 12, 2002. After December 12, 2002 there will be no refund.
=20
MODE OF PAYMENT: All payments should be made by a crossed cheque or=20
demand draft in favour of "International Institute of Information Technol=
ogy,=20
Hyderabad"=20
=20
Please return the filled in form along with a cheque or demand=20
draft to ICON 2002 Secretariat.
=20
ICON-2002 Secretariat
Language Technologies Research Centre
International Institute of Information Technology
Gachibowli, Hyderabad - 500 019
Email Id: ico...@ii...
******************************************************************
|
