[1] From: Priscilla Rasmussen <rasmusse@cs.rutgers.edu> (621)
Subject: ANLP-97 Registration Brochure
[2] From: Priscilla Rasmussen <rasmusse@cs.rutgers.edu> (100)
Subject: ACL/EACL-97 Workshop Call For Papers
[3] From: Remi Zajac <rzajac@crl.nmsu.edu> (147)
Subject: IJCAI-97 Workshop on Ontologies and Multilingual NLP
--[1]----------------------------------------------------------------
Date: Tue, 4 Feb 1997 09:52:12 -0500 (EST)
From: Priscilla Rasmussen <rasmusse@cs.rutgers.edu>
Subject: ANLP-97 Registration Brochure
ASSOCIATION FOR COMPUTATIONAL LINGUISTICS
FIFTH APPLIED NATURAL LANGUAGE PROCESSING CONFERENCE
31 March - 3 April, 1997
Washington Marriott Hotel, Washington D.C.
INVITED TALK
Government Perspectives on the Future of Language Technologies
(tentative title)
Ruth A. David, Deputy Director
Science and Technology, Central Intelligence Agency
NOTICE CONTENTS
Application for PreRegistration
Registration Information and Directions
Accommodation Information
Program Information
Tutorial Descriptions
Workshop Description
APPLICATION FOR PREREGISTRATION (by 28 February)
5th Applied Natural Language Processing Conference
31 March - 3 April, 1997, Washington Marriott Hotel, Washington, D.C.
NAME _______________________________________________________________________
Last First Middle
ADDRESS ____________________________________________________________________
AFFILIATION (for badge) ____________________________________________________
TELEPHONE __________________________________________________________________
E-MAIL ADDRESS _____________________________________________________________
REGISTRATION INFORMATION (circle fee)
NOTE: Only those whose ACL membership is paid for the 1997 calendar year
can register as members; if you have not, register at the
``non-member'' rate.
REGULAR NON- STUDENT STUDENT
MEMBER MEMBER* MEMBER NONMEMBER*
by Feb. 28 $200 $275 $100 $140
late/onsite $260 $335 $120 $160
*Non-member registration fee includes ACL membership for 1997; do not pay
non-member fee for BOTH the registration and the tutorials.
TUTORIAL INFORMATION (circle fee)
To attend two tutorials, pay twice the amount shown.
REGULAR NON- STUDENT STUDENT
MEMBER MEMBER* MEMBER NONMEMBER*
EACH Tutorial:
by Feb. 28 $125 $185 $85 $125
late/onsite $150 $210 $95 $135
*Non-member registration fee includes ACL membership; do not pay the
non-member fee for BOTH the registration and the tutorials.
Monday morning tutorials -- select at most ONE:
[ ] Creating and Using Automatic Lingustic Annotation Software
[ ] Building Applied Natural Language Generation Systems
Monday afternoon tutorials -- select at most ONE:
[ ] Using Speech Recognition
[ ] Building Information Extraction Systems
BANQUET TICKETS ($55 each): $____________________
SPECIAL MEALS: If you have special dietary preferences for the banquet,
please contact John White (white_john@prc.com)
EXTRA PROCEEDINGS for REGISTRANTS ($30 each): $__________________
PROCEEDINGS ONLY ($30 members; $60 others): $____________________
NOTE: there is no deadline for Proceedings Only orders (May 1997 delivery)
TOTAL PAYMENT --- MUST BE INCLUDED: $____________________________
(Registration, tutorials, banquet, extra proceedings)
METHOD OF PAYMENT:
[ ] Visa or MasterCard: Number________________________________________
Expiration Date __________/___________
month / year
Name as it appears on card: ______________________________________
[ ] Attached check payable to Association for Computational Linguistics
or ACL
SEND TO:
ACL phone +1-908-873-3898
Priscilla Rasmussen fax +1-908-873-0014
P.O. Box 6090 acl@bellcore.com
Somerset, NJ 08875, USA
REGISTRATION INFORMATION and DIRECTIONS
Technical Program: Tuesday, April 1 - Thursday, April 3
Tutorials: Monday, March 31
Post-conference Workshop: Friday, April 4
For this information and further details about ACL and the ANLP-97 Conference,
see the WWW page:
http://www.cs.columbia.edu:80/~acl/home.html
PREREGISTRATION MUST BE RECEIVED BY FEBRUARY 28. After that date,
it will be preferable to register at the conference itself. Complete the
attached preregistration form and send it with payment to ``Association
for Computational Linguistics'' or ``ACL'' to ACL, P.O. Box 6090,
Somerset, NJ 08875 USA. phone +1-908-873-3898, fax +1-908-873-0014.
Payment must be either by check, Visa or MasterCard.
REGISTRATION: Includes one copy of the Proceedings, available at the
conference. Additional copies of the Proceedings, $30 for members and $60
for nonmembers, may be ordered on the registration form or prepaid by mail
to the ACL Office. For those who are unable to attend the conference but
want the proceedings, there is a special entry line at the bottom of the
preregistration form.
SITE: ANLP-97 will be held at the Washington Marriott Hotel, 1221 22nd
Street, N.W., Washington, D.C.
TUTORIALS: Four tutorials will be held the day before the conference,
Monday, March 31. Attendance in each tutorial is limited. Preregistration
is essential to ensure a place and guarantee that syllabus materials will
be available.
TUTORIAL RECEPTION: Reception and a cash bar for tutorial attendees
will be held on Sunday evening, March 30.
OPENING RECEPTION: The opening reception will be held on Monday evening,
March 31.
BANQUET: The conference banquet will be held on Wednesday evening,
April 2, on the Spirit of Washington cruise line. A ride through the
thick of the cherry blossoms will begin a three-hour cruise down the
legendary Potomac river, from which you will see the Washington Monument,
National Cathedral, and the lights of Old Town Alexandria. Music of the
river and the region will accompany the tour.
LOCAL ARRANGEMENTS: Specific inquiries regarding local arrangements may
be directed to John White, (white_john@prc.com), +1-703-556-1899. For
questions regarding accommodations, special needs or assistance, please
contact the Washington Marriott Hotel, +1-202-872-1500.
EXHIBITS AND DEMONSTRATIONS: A number of publisher exhibits and
computer demonstrations have been scheduled. For information on
arranging demonstrations and exhibits mail white_john@prc.com or
call +1-703-556-1899. For exhibits of research systems, the charge
is a nominal $40. The fee for exhibiting a commercial system (intended
for sale as a product) is $250.
SPONSORS: The organizers are most grateful to the following organizations
for their generous offer of monetary and technical support:
AT&T Labs - Research
SRA International
Isoquest Inc.
Logos Development Corporation
PRC Inc.
Federal Intelligent Document Understanding Laboratory
The Association is seeking additional sponsors for the conference. Please
contact John White if you are interested in serving as a sponsor and to
discuss types of recognition your generosity will receive.
RECREATION: The Washington Marriott provides a variety of modern
recreational facilities, including indoor pool, sauna, jacuzzi, exercise
room with universal equipment, free weight, Stairmaster and other workout
facilities. These facilities are free to hotel guests.
CLIMATE AND DRESS: Early April is cherry blossom time in Washington. The
temperature can vary from rather raw (highs of 50F / 10C) to quite pleasant
(highs of 75F / 24C). Light rain is quite possible at some point during the
conference, and it is often breezy during this time. The visitor should be
prepared for all of these contingencies, to fully enjoy Washington's most
beautiful time of year.
SIGHTSEEING: Washington presents an intriguing blend of the driven pace
of a Northeastern metropolis with the charm of a Southern coastal town.
The city is, of course, legendary for the monuments and museums, of which
most are near the conference site. However, it is a treat just to walk
around in the urban neighborhoods in the vicinity of the Washington Marriott
-- Washington Circle, Dupont Circle, Foggy Bottom, George Washington
University. A similarly interesting walk is the de facto financial district,
along K street (NW) from about 23rd to 14th. You will find Reiter's
Scientific Books just down the street, around 20th and K, which will gain
your interest, time, and your book-buying dollars. The area restaurants
cover an extraordinary range of culinary types, from various regions of
India, to very good barbecue, to stunning vegetarian collard greens.
Like most areas these days, there are several notable local breweries,
including Old Heurich (D.C.) and Old Dominion (Virginia), along with many
brew-pubs, mostly excellent. Virginia produces a credible wine collection,
abundantly available in the DC area. There will be several events associated
with the annual National Cherry Blossom Festival underway during and after
the conference period, including concerts, parades, races, art exhibitions,
etc. The conference site is roughly 10 blocks from the portion of the Mall
that contains the Vietnam and Korean Veterans Memorials, and the Lincoln
Memorial. Further toward the omnipresent Capitol dome you will pass the
Washington Monument on your way to the Smithsonian, a gigantic cluster of
buildings on both sides of the Mall that will capture your attention
forever if you let it. Some of the best museums in the world, all free.
About 8 blocks in a slightly different direction will bring you to the
front of the White House at (you guessed it) 16th and Pennsylvania. Yet
another trek in the opposite direction, 10 or so blocks will take you to
the heart of Georgetown, a bustling, youthful area, both intellectual
and outrageous.
DIRECTIONS: BY AIR: Three airports serve the Washington / Baltimore
area. The two most convenient for the Washington Marriott are Washington
National (just across the Potomac) and Dulles International (about 20 miles
inland).
>From National: Exit the airport and take the George Washington
Parkway westbound}. Cross over the Memorial bridge. Bear to the left
at the end of the bridge, and take your first left onto 23rd Street.
Follow 23rd Street to I (eye) Street and make a right turn. Make your
first left onto 22nd street. The hotel will be five blocks up on the
right hand side.
>From Dulles: Follow I-66 Eastbound to the Constitution Avenue exit.
Make a left turn onto 18th Street. Make a left onto M Street. Proceed
on M to 22nd Street and make a right turn. The hotel will be on the
right hand side.
BY CAR: From the North, follow I-95 South to I-495 West toward
Silver Spring. If you are astonished by some architecture about 5 miles
later, you are going the right way. Exit I-495 at the Connecticut Avenue
/ Chevy Chase exit. Continue on Connecticut Avenue for nine miles and
make a right turn on M Street. Proceed five blocks to 22nd Street and
make a right turn. The hotel is on the right.
>From the South, take I-95 North to I-395 North. Follow signs for the
Memorial Bridge. Then follow the National Airport directions.
BY METRO: The Washington Metro is a subway/bus transit system that has
two stops near the hotel: Foggy Bottom / GWU (23rd near Washington Circle)
on the Orange and Blue Lines; and Farragut North (K and 17th streets) on
the Red Line.
PARKING: Parking at the Marriott is $15 per night for hotel guests.
Parking garages are available nearby for comparable prices. Street
parking is hard to find.
FOREIGN CURRENCY EXCHANGE: For most currencies, exchanges can be made
readily either at the airports or at banks in the vicinity of the hotel.
ACCOMMODATION
Accommodations are made available at a special conference rate at the
Washington Marriott, the site of the conference. A block of rooms has
been designated for the conference at special rates, including a small
number of rooms that may be reserved at the prevailing U.S. Government
per diem rate. In addition, the Marriott will allow students to share
rooms up to four persons, at reduced rates. Unfortunately, during the
academic year, no dormitory housing is available.
To make a reservation, contact the Washington Marriott Hotel,
+1-800-344-4445 or +1-202-872-1500. All reservations must be guaranteed
either by credit card or by a first night room deposit. Inform the hotel
that you are attending the Association for Computational Linguistics
Applied Natural Language Processing Conference. In order to receive
conference rates, reservations must be received by March 7, 1997.
Rates: Singles: $135.00 per night (plus applicable taxes of approximately
13%). Doubles-to-Quads: $140.00 per night (plus taxes). Ask about U.S.
government rates, if applicable, ($124.00 inclusive -- a limited number are
available).
FIFTH APPLIED NATURAL LANGUAGE PROCESSING CONFERENCE
31 March - 3 April, 1997
Washington Marriott Hotel, Washington D.C.
PROGRAM AT A GLANCE
----------------------------------------------------------------------------
Last revised January 27, 1997
Time schedule subject to revision.
PROGRAM COMMITTEE: Ralph Grishman (Chair), New York University. Members:
Chinatsu Aone, SRA Corporation, Rusty Bobrow, BBN, Martha Evens, Illinois
Institute of Technology, Lynette Hirschman, MITRE Corporation, Eduard Hovy,
University of Southern California/Information Sciences Institute,
Yuji Matsumoto, Nara Institute of Science and Technology, Boyan Onyshkevych,
U. S. Dept. of Defense, Tomek Strzalkowski, General Electric Corporate
Research and Development, Henry Thompson, University of Edinburgh,
Hans Uszkoreit, DFKI Saarbruecken, Marc Vilain, MITRE Corporation.
Sunday, March 30
6:00-8:00 Tutorial Registration, 2nd Floor
6:00-8:00 Tutorial Reception, 2nd Floor
Monday, March 31
Tutorials
8:00- 3:00 Tutorial Registration, 2nd Floor
9:00-12:30 Creating and Using Automatic Linguistic Annotation Software
9:00-12:30 Building Applied Natural Language Generation Systems
2:00- 5:30 Using Speech Recognition
2:00- 5:30 Building Information Extraction Systems
6:00- 9:00 Conference Registration, 2nd Floor
7:00-10:00 Conference Reception
Tuesday, April 1
8:00- 5:30 Conference Registration, 2nd Floor
9:00- 9:15 Introductions
9:15-10:00 Invited Talk Government Perspectives on Ruth A. David
the Future of Language
(tentative title)
10:00-10:30 BREAK
Track A: Track B:
10:30- 5:00 Spoken Language and Dialog Syntax and Morphology
Wednesday, April 2
Track A: Track B:
9:00-11:10 Computer-Aided Language Information Extraction
Learning
11:10-12:00 Text Checking and other Continued
Applications
2:00- 3:30 Continued Document Management
3:30- 5:00 Demonstrations
Thursday, April 3
Track A: Track B:
9:00-11:00 Text Generation Multilingual Systems
11:00- 1:30 Information Retrieval and Acquisition of Lexical
Summarization Information from Corpora
1:30- 4:00 Continued Continued
-----------------------------------------------------------------------------
-----------------------------------------------------------------------------
PROGRAM IN DETAIL
8:30- 5:30 Conference Registration, 2nd Floor
(Tues.-Thurs.)
Tuesday, April 1: Track A
SPOKEN LANGUAGE and DIALOG
10:30 CommandTalk: A Robert Moore, John Dowding,
Spoken-Language Interface for Harry Bratt, J. Mark Gawron,
Battlefield Simulations and Adam Cheyer
11:00 Natural Language in Four Kenneth Wauchope, Stephanie Everett,
Spatial Interfaces Dennis Perzanowski, and Elaine Marsh
11:20 High Performance Marsal Gavalda, Klaus Zechner, and
Segmentation of Spontaneous Gregory Aist
Speech Using Part of Speech
and Trigram Word Information
A Maximum Entropy Approach
11:40 Identifying Sentence Jeffrey Reynar and Adwait Ratnaparkhi
Boundaries
12:00 L u n c h
1:30 Unification-based Michael Johnston, Phil Cohen, Liang
Multimodal Integration for Chen, Joshua Clow, David McGee,
Distributed Simulation James Pittman, and Ira Smith
2:00 Natural Language Dialog Stephen Busemann, Thierry Declerck,
Service for Appointment Luca Dini, Judith Klein, and
Scheduling Agents Sven Schmeier
2:30 Insights into the Dialog Jan Alexandersson, Norbert Reithinger,
Processing of Verbmobil and Elisabeth Maier
3:00 B r e a k
3:30 An Evaluation of Strategies Ronnie Smith
for Selective Utterance
Verification for Spoken
Natural Language Dialog
4:00 Name Pronunciation in Bernd Mobius and Stefanie Jannedy
German Text-to-speech
Synthesis
4:30 Applying Repair Processing Yue-Shi Lee and Hsin-Hsi Chen
4:30 in Chinese Homophone
Distinction
Tuesday, April 1: Track B
SYNTAX and MORPHOLOGY
10:30 A Non-projective Dependency Pasi Tapanainen and Timo Jarvinen
Parser
11:00 Incremental Finite-State Salah Ait-Mokhtar and
Parsing Jean-Pierre Chanod
11:30 Developing a Hybrid NP Atro Voutilainen and Lluis Padro
Parser
12:00 L u n c h
1:30 An Annotation Scheme for Wojciech Skut, Brigitte Krenn, and
Free Word Order Languages Thorsten Brants
2:00 The Domain Dependence of Satoshi Sekine
Parsing
2:30 Automatic Acquisition of Pieter Theron and Ian Cloete
Two-level Morphological
Rules
3:00 B r e a k
3:30 Probabilistic and Rule-based Barbora Hladka and Jan Hajic
Tagger of an Inflective
Language
4:00 Cseg&Tag1.0: A Practical Sun Maosong, Shen Dayang, and
Word Segmenter and POS Huang Changning
Tagger for Chinese Texts
Wednesday, April 2: Track A
COMPUTER-AIDED LANGUAGE LEARNING
9:00 The NLP Role in Animated Michael Schoelles and Henry
Conversation for CALL Hamburger
9:30 Reading more into Foreign John Nerbonne, Lauri Karttunen.
Languages Elena Paskaleva, Gabor Proszeky,
10:00 Large-Scale Acquisition Bonnie Dorr
of LCS-Based Lexicons for
Foreign Language Tutoring
10:30 B r e a k
TEXT CHECKING & other applications
11:10 A prototype of Grammar Tomas Holan, Vladimir Kubon,
Checker for Czech and Martin Platek
11:40 Techniques for Karel Oliva
Accelerating a Grammar
Checker
12:00 L u n c h
1:30 EasyEnglish: A Tool for Arendse Bernth
Improving Document
Quality
2:00 Contextual Spelling Michael Jones and James Martin
Correction Using Latent
Semantic Analysis
2:30 An Automatic Scoring Jill Burstein
System for Advanced
Placement Biology Exams
3:00 Dutch Sublanguage Peter Spyns, Eric Baert,
Semantic Tagging combined Georges De Moor, Ngo Thanh Nhan,
with Mark-Up Technology and Naomi Sager
Wednesday, April 2: Track B
INFORMATION EXTRACTION
9:00 A Statistical Profile of the David Palmer and David Day
Named Entity Task
9:20 Nymble: a High-Performance Daniel Bikel, Scott Miller,
Learning Name Finder Richard Schwartz, and Ralph
Weischedel
9:50 Disambiguation of Proper Nina Wacholder and Yael Ravin
Names in Text
10:20 B r e a k
11:10 An Information Extraction Guenter Neumann, Rolf Backoven,
Core System for Real World Judith Baur, Markus Becker, and
German Text Processing Christian Braun
11:40 Layout & Language: Matthew Hurst and Shona Douglas
Preliminary experiments in
assigning logical structure
to table cells
12:00 L u n c h
1:30 Building a Generation Dragomir Radev and Kathleen
Knowledge Source using McKeown
Internet-Accessible Newswire
DOCUMENT MANAGEMENT
2:00 Using SGML as a Basis for David McKelvie, Chris Brew, and
Data-Intensive NLP Henry Thompson
2:30 Software Infrastructure for Hamish Cunningham, Kevin Humphreys,
Natural Language Processing Robert Gaizauskas, and Yorick Wilks
3:00 An Open Distributed Remi Zajac
Architecture for Reuse an
Integration of Heterogenous
NLP Components
Thursday, April 3: Track A
TEXT GENERATION
9:00 Customizable Descriptions Benoit Lavoie, Owen Rambow,
of Object-Oriented Models and Ehud Reite
9:30 CogentHelp: NLG meets SE Michael White and Ted Caldwell
in a tool for authoring
dynamically generated
on-line help
10:00 A Fast and Portable Benoit Lavoie and Owen Rambow
Realizer for Text
Generation Systems
10:30 B r e a k
11:00 Multilingual Generation and Harold Somers, Alex Rogers, Joaki
Summarization of Job Adverts: Nivre, Annarosa Multari, Torbjorn
the TREE Project Lager, Luca Gilardoni, Jeremy Ellman,
and Bill Black
11:30 Language Generation for Kathleen R. McKeown, Shimei Pan,
Multimedia Healthcare James Shaw, Desmond Jordan, and
Briefings Barry A. Allen
12:00 L u n c h
INFORMATION RETRIEVAL AND SUMMARIZATION
1:30 Identifying Topics by Position Chin-Yew Lin and Eduard Hovy
2:00 An Automatic Extraction Fumiyo Fukumoto, Yoshimi
of Key Paragraph Based Suzuki, and Jun'ichi Fukumoto
On Context Dependency
Building Effective
2:30 Queries in Natural Tomek Strzalkowski, Fang Lin,
Language Information Jose Perez-Carballo, and
Retrieval Jin Wang
3:00 B r e a k
3:30 Construction and Joe Zhou and Troy Tanner
Visualization of Key
Term Hierarchies
4:00 Fast Statistical Checgxiang Zhai
Parsing of Noun Phrases
for Document Indexing
Thursday, April 3: Track B
MULTILINGUAL SYSTEMS
9:00 An English to Turkish Cigdem Turhan
Machine Translation System
Using Structural Mapping
9:30 An Interactive Translation Kiyoshi Yamabana, Kazunori Muraki,
Support Facility for Shin-ichiro Kamei, Kenji Satoh,
Non-Professional Users Shinichi Doi, and Shinko Tamura
10:00 An Intelligent Multilingual Chinatsu Aone, Nicholas Charocopos,
Information Browsing and and James Gorlinsky
Retrieval System Using
Information Extraction
10:30 B r e a k
ACQUISITION of LEXICAL INFORMATION from CORPORA
11:00 Semi-automatic Acquisition Philip Resnik and I. Dan Melamed
of Domain-specific Bilingual
Translation Lexicons
11:30 Mixed-Initiative Development David Day, John Aberdeen, Lynette
of Language Processing Hirschman, Robyn Kozierok,
Systems Patricia Robinson, and Marc Vilain
12:00 L u n c h
1:30 Automatic Extraction of Ted Briscoe and John Carroll
Subcategorization from
Corpus
2:00 Learning Subcategorization Takehito Utsuro and Yuji Matsumoto
Preferences with a Hidden
Variable: Coping with Case
Dependencies and Noun Class
Generalizations
2:30 A Workbench for Finding Andrei Mikheev and Steven Finch
Structure in Texts
3:00 B r e a k
3:30 Automatic Selection of Class Paola Velardi and Clessandro
Labels from a Thesaurus for Cucchiarelli
an Effective Semantic
Tagging of Corpora
4:00 Sequential Model Selection Ted Pedersen, Rebecca Bruce,
for Word Sense and Janyce Wiebe
Disambiguation
FIFTH APPLIED NATURAL LANGUAGE PROCESSING CONFERENCE
TUTORIAL PROGRAM
March 31, 1997
Creating and Using Automatic Linguistic Annotation Software
9:00-12:30
Eric Brill, Department of Computer Science and Center for Language and
Speech Processing, Johns Hopkins University
In order to perform any sophisticated natural language processing task,
it is necessary to first discover the underlying linguistic structure of
the input. Depending on the task, this might include information such as
parts of speech, word senses, phrase structure, different types of names,
etc. Recently a number of approaches have been developed for automatically
training programs to provide such annotations. We will survey these
approaches and discuss their advantages and disadvantages. The most
accurate automatically trained systems typically require large
manually-annotated corpora for training, thereby making them expensive
to port across domains or languages for which such corpora are not readily
available. We will describe methods that allow rapid porting, including:
learning without an annotated corpus, adapting an already-trained program
to a new domain with minimal resources, and methods for combining human
intuitions with automatic acquisition.
Building Applied Natural Language Generation Systems
9:00-12:30
Ehud Reiter, Computer Science Department, University of Aberdeen, Scotland,
and Robert Dale, Microsoft Institute, Macquarie University, Australia
Natural language generation systems produce understandable texts in
English or other human languages from some underlying non-linguistic
representation of information. NLG systems combine knowledge about language
and the application domain to automatically produce documents, reports,
explanations, help messages, and other kinds of texts.
The late 1990s is an exciting time for applied NLG. 10 years ago NLG was
purely a research activity, but in 1997 there are several fielded NLG
systems in everyday use, and many more systems under development. In this
tutorial, we will describe some of the techniques that are being used to
build practical working applications today; we will also provide pointers
to leading-edge research developments in the field. The material is based
around a popular architectural model of NLG that encompasses the three
stages of text planning, sentence planning and linguistic realisation.
We will include a case study showing how to construct an NLG system which
produces textual meteorological summaries from underlying numeric data sets.
The tutorial should be useful for managers, implementors, and researchers.
For managers, it will provide a broad overview of the field and what is
possible today; for implementors, it will provide a realistic assessment
of available techniques; and for researchers, it will highlight the issues
that are important in current applied NLG projects.
Using Speech Recognition
2:00-5:30
Judith Markowitz, J. Markowitz Consultants
Talking is a fundamental and ubiquitous mode of communication between
humans. The idea of extending speech to verbal interaction with machines
has produced powerful icons, such as Arthur Clark's Hal; Kit, the
futuristic car; and StarTrek computers.
Researchers and developers have been designing speech recognition systems
for almost 50 years, and the fruit of their labor is a growing number of
diverse speech-controlled systems, including speech-to-text dictation
products, voice-activated dialing systems, and telephone messaging tools.
The presentation addresses three major questions about speech recognition:
What is speech recognition?
How does it work?
What is it used for?
Answers to these questions include examination of speaker modeling,
vocabulary creation, grammar, and input channels. The presentation will
be accompanied by videotaped examples of existing systems and products.
Building Information Extraction Systems
2:00-5:30
Douglas E. Appelt and David Israel, Artifical Intelligence Center,
SRI International
This tutorial will cover the what and the how of Information Extraction
(IE) systems. First we characterize the range of tasks usually intended
for IE techniques, and then describe the various approaches to
implementing these techniques, discussing the advantages and disadvantages
of each. Most IE systems process texts in sequential steps ("phases")
ranging from lexical and morphological processing, recognition and typing
of proper names, parsing of larger syntactic constituents, and resolution
of anaphora and coreference. Finally, IE systems have a domain phase that
recognizes events and relationships relevant to the specific IE task. We
shall discuss various approaches to each of these phases in turn, and
examine their suitability for different types of IE problems. We will
discuss the problems and advantages of incorporating various external
resources into extraction systems, including large lexicons, gazetteers,
and part-of-speech taggers, and conclude with a discussion of template
design principles that can have a significant impact on the difficulty
of the IE task.
POSTCONFERENCE WORKSHOP
on
TAGGING TEXT WITH LEXICAL SEMANTICS: WHY, WHAT, AND HOW?
SIGLEX 97 -- 4th Meeting of the Special Interest Group on the Lexicon
Friday and Saturday, April 4-5, 1997
Friday: HAND TAGGING
Invited talk
Hwee Tou Ng
(Defence Science Organisation, Singapore)
Experience in WordNet sense tagging in the Wall Street Journal.
J. Wiebe, J. Maples, L. Duan, and R. Bruce
(New Mexico State U., USA and S. Methodist U., USA)
Desiderata for tagging with WordNet synsets or MCCA categories.
K.C. Litkowski
(CL Research, USA)
A frame-semantic approach to semantic annotation.
J.B. Lowe, C.F. Baker, and C.J. Fillmore
(U. of California, USA)
A lexicon for underspecified semantic tagging.
P. Buitelaar
(Brandeis U., USA)
LUNCH
Invited talk
Christiane Fellbaum
(Princeton U. and Rider U.)
Afternoon working sessions
Saturday: AUTOMATED METHODS
Measuring semantic entropy.
I.D. Melamed
(U. of Pennsylvania, USA)
Sense tagging: semantic tagging with a lexicon.
Y. Wilks and M. Stevenson
(U. of Sheffield, UK)
Selectional preference and sense disambiguation.
P. Resnik (U. of Maryland, USA)
Investigating complementary methods for verb sense pruning.
H. Jing, V. Hatzivassiloglou, R. Passonneau, and K. McKeown
(Columbia U., USA)
Semantic bootstrapping from corpora.
R. Basili, M. Della Rocca, and M. T. Pazienza
(U. Tor Vergata Roma, Italy)
Sense tagging in Action.
A. Harley and G. Glennon
(Cambridge Language Services, UK)
LUNCH
A perspective on word sense disambiguation methods and their evaluation.
P. Resnik and D. Yarowsky
(U. of Maryland, USA and John Hopkins U., USA)
Afternoon working sessions
PROGRAM COMMITTEE
Marc Light (chair), Martha Evens, Helmut Feldweg, Michael Johnston, Doug
Jones, Kevin Knight, Boyan A. Onyshkevych, Martha Palmer, Philip Resnik,
Evelyne Viegas, David Yarowsky, Annie Zaenen.
REGISTRATION:
Registrations via email to light@sfs.nphil.uni-tuebingen.de with the
Subject line "SIGLEX 96 Registration" are strongly preferred. The
registration fee is US$55. Acceptable forms of payment are checks in
US dollars payable to ``Marc Light'', credit card (VISA/Mastercard)
payment, bank transfer in US dollars to Marc Light (account
num. 19857012), Volksbank T"ubingen (routing num. 64190110) with
message ``SIGLEX-97''. Please submit the following form (see also
http://www.sfs.nphil.uni-tuebingen.de/~light/semtag_ws.html)
regardless of payment option used:
Name:
Institution: <for name tag>
Address: <postal address>
Email:
Phone and Fax:
Payment: <specify check, credit card, or bank transfer>
Credit card type: <Visa/Mastercard> only if paying by credit card
Credit card info: <name on card, card number, expire date>
Dietary requirements: <vegetarian, etc.>
Please send to:
Marc Light
SfS-Computerlinguistik
Wilhelmstrasse 113
D-72074 T"ubingen
Germany
email: light@sfs.nphil.uni-tuebingen.de
--[2]----------------------------------------------------------------
Date: Tue, 4 Feb 1997 09:51:42 -0500 (EST)
From: Priscilla Rasmussen <rasmusse@cs.rutgers.edu>
Subject: ACL/EACL-97 Workshop Call For Papers
------------------------------------
FIRST CALL FOR PAPERS
COMPUTATIONAL PHONOLOGY
Third Meeting of the ACL Special Interest Group
in Computational Phonology (SIGPHON 97)
In conjunction with
ACL'97/EACL'97 Joint Conference
Madrid, Spain, 11th [or 12th?] July 1997
------------------------------------
A. Description of the workshop
The workshop will be devoted to all areas of computation, as applied to
contemporary phonology. Papers will be on substantial, original, and
unpublished research on any aspect of computational phonology,
including (but not limited to) finite-state, connectionist and logical
techniques; formalisms, implementations and complexity results;
computational, mathematical and psychological models; and the
integration of phonology with grammar and speech. Theoretical and
applied studies are equally welcome.
The workshop will occupy the whole day, with c. 10-12 papers, and a
general discussion to conclude.
B. Organizing committee and program committee.
The organizing committee will consist of the following members of the
SIGPHON executive:
John Coleman (University of Oxford)
Steven Bird (University of Edinburgh)
Bob Berwick (MIT)
Andras Kornai (IBM Almaden Research Center)
The program committee will consist of the executive plus other members
whom the executive may invite to strengthen the referee pool in
particular areas. External referees will be invited for any paper submitted
by a member of the program committee.
C. Primary contact
All correspondence should be sent to:
John Coleman
Oxford University Phonetics Laboratory
41 Wellington Square
Oxford OX1 2JF, UK
Tel. +44 (1865) 270444
Fax. +44 (1865) 270445
email: john.coleman@phonetics.oxford.ac.uk
D. Submission of papers
Papers should describe unique work; completed work is preferable to
intended work, but in any event the paper should clearly indicate the
state of completion of the reported results. Papers must not exceed
10 printed A4 pages.
The entire process from initial submission, to reviewing and final
submission will be handled electronically. The initial submission may
either be in plain ascii, compressed postscript, or else should follow
the ACL submission style (aclsub.sty) retrievable from the ACL LISTSERV
server (access to which is described below) which requires TeX 3.14 or
LaTeX 2.09. (La)TeX submissions that include (possibly) separate
postscript figure files must be packaged using the aclpkg.script (also
available from the LISTSERV). ASCII or postscript is preferred, however.
Final accepted versions MUST be (la)tex files following aclsub.sty, if
necessary packaged using aclpkg.script.
A title page containing the title, a short abstract, author names and
addresses, should be attached to the submission. Postscript figures
following psfig.sty may be included.
Submissions should be sent via email to: john.coleman@phonetics.oxford.ac.uk
Acknowledgment of receipt will be sent to the first author of the
paper.
IMPORTANT DATES
MARCH 31, 1997 Initial submissions due
APRIL 25, 1997. Notification of acceptance
MAY 25, 1997. Receipt of final accepted papers
E. Registration
As the costs of the workshop have not yet been finalized, registration
information will be sent out later. Note that all participants must
register for the main ACL/EACL conference. Information about the main
conference is available from the URL http://horacio.ieec.uned.ed/cl97/
There will be an additional registration fee for the workshop of
approximately US $35, which will include a copy of the workshop
proceedings.
ACL/EACL reserves the right to cancel any workshop if the number of
participants is below 25 persons.
F. AUDIO-VISUAL NEEDS.
An overhead projector will be available. Requests for other A/V
equipment should be directed to sigphon96@research.att.com
G. ACL LISTSERV
LISTSERV is a facility set up at Columbia University's Department of Computer
Science to allow access to an electronic document archive by electronic
mail. Requests for files from the archive should be sent as e-mail messages to:
listserv@cs.columbia.edu
with an empty subject field and the message body containing the request com-
mand. The most useful requests are "help" for general help on using LISTSERV,
"index ACL96" for the current contents of the ACL archive and
"get ACL96 <file>" to get a particular file named <file> from the archive.
For example, to get the ACL96 modelsub.tex file, send a message with the
following body:
get ACL96 modelsub.tex
Answers to requests are returned by e-mail. Since the server may have many
requests for different archives to process, requests are queued up and may take
awhile (say, overnight) to be fulfilled. The ACL archive can also be accessed
by anonymous FTP. Here is an example of how to get the same file by FTP:
$ ftp cs.columbia.edu
Name(cs.columbia.edu:trisha): anonymous
Password:trisha@cis.upenn.edu < not echoed >
ftp> cd ACL96
ftp> get modelsub.tex.Z
ftp> quit
$ uncompress modelsub.tex.Z
--[3]----------------------------------------------------------------
Date: Tue, 4 Feb 1997 09:45:22 -0500 (EST)
From: Remi Zajac <rzajac@crl.nmsu.edu>
Subject: IJCAI-97 Workshop on Ontologies and Multilingual NLP
**********************************************************************
Call for Submissions Please Distribute Widely
**********************************************************************
IJCAI-97 Workshop on
Ontologies and Multilingual NLP
Nagoya, Japan, August 23-25, 1997
(Web page: <a ref="http://crl.nmsu.edu/Events/IJCAI/">
Workshop on Ontologies and Multilingual NLP</a>)
Background
==========
A number of ontology-related workshops have been held in the past
years (e.g., 1993 in Padua, 1995 IJCAI, 1996 ECAI, 1997 AAAI Spring
Symposium, etc.). However, none of them concentrated centrally on
applications of world modeling to multilingual Natural Language
Processing (NLP).
Ontologies for knowledge-based computing and especially for Natural
Language Processing are steadily reaching a level of sophistication
and size which make them increasingly useful to the resolution of
problems in real-world NLP applications. The recent creation of an ad
hoc ANSI working group on standardization of ontologies is an
indication of the maturity of the field. More and more ontology-based
systems are being built for multilingual applications (e.g.,
multilingual machine translation, multilingual information
retrieval). However, most of the language-processing oriented
ontologies that have been built so far have English or another
language (e.g., Japanese or Spanish) as the basis (e.g., WordNet, EDR,
Pangloss, etc.). Since there is a growing need for multilingual
applications of these ontologies, it is natural to ask the following
questions: Are any of these ontologies actually used in a multilingual
setting? Can we characterize the degree of independence of an ontology
from the natural language it is based on? What are the necessary
properties of a truly multilingual (or universal) ontology? Is it
possible to obtain a language-neutral ontology from a
language-dependent ontology? What applications truly need multilingual
(or language-neutral) ontologies? How do we separate language-specific
(or lexical) information from ontological knowledge? How can the
depth of knowledge in the ontology be balanced with the needs of an
application? What are the prospects of automating ontology
acquisition? What is the relationship between an ontology as the
repository of general knowledge about the world and knowledge about
particular individuals - people, places, organizations, events,
etc.?
These and many more questions must be discussed much more widely than
they have been till now. Many of the previous workshops were devoted
to more formal issues in ontology building, such as the knowledge
representation schemata, closures, formal properties of ontologies,
and so on. Moreover, they included the discussion of small ontologies
that cover a very narrow domain of problem solving; NLP typically
requires a broad-coverage ontology. The hypothesis of using
interlingual representations based on an ontology is at least 50 years
old. It was originally formulated in the framework of machine
translation. However, few systems to date have tested this hypothesis,
for MT or other applications, by implementing a large-scale
interlingua-based system using a language-independent ontology. This
workshop will debate the benefits, costs and competitiveness of such
an approach to solving semantic and cross-language problems for MT,
IR, and other NLP applications.
Audience
========
The workshop is open to all members of the AI and NLP community. The
workshop is intended for researchers and practitioners in
knowledge-based NLP, artificial intelligence and computational
linguistics who have been working on large scale knowledge-based
resources, ontologies, multilingual lexical semantics, interlinguas,
and their applications. Reports of actual work including problems and
solutions in the design, construction and use of ontologies are
strongly encouraged but more theoretical work (grounded on actual work
on ontologies) aimed at defining the limits, constraints and
directions for large-scale practical language-neutral ontologies is
welcome as well.
Issues
======
Issues to be addressed include but are not limited to:
- Design of language-neutral ontologies.
- Acquisition problems in multilingual ontologies.
- Multilingual applications of ontologies.
- Multilingual ontologies and terminological knowledge bases.
- Ontologies and interlinguas.
- Standardization of ontologies: issues of multilinguality.
- Ontologies and Lexicons.
- Sharing and standardization of language-independent ontologies for NLP.
- Costs and competitiveness of ontology-based solutions vis-a-vis
corpus-based and transfer-based methods for multilingual NLP.
Format of the Workshop
======================
The workshop will include twelve presentation periods which will be
divided into ten-minute presentations of positions followed by
20-minute discussions.
The attendance will be limited to 20 active participants. Papers will
be circulated among participants several weeks before the
workshop. Presentation will be short, under 15 minutes (10 minutes
preferably) with 20 minutes reserved for exchanges.
We encourage the authors to focus on the salient points of their
presentation and identify possible controversial positions. We
encourage authors not to repeat as is what has been already written in
the paper. There will be ample time set aside for informal and panel
discussions and audience participation.
Please note that workshop participants are required to register at
the main IJCAI-97 conference.
Submission Information
======================
Timetable
---------
- March 15, 1997: Deadline for reception of submissions.
- May 1, 1997: Notification of acceptance.
- July 1, 1997: Deadline for reception of camera-ready copy.
Format
------
Submissions must not exceed 6 pages in camera-ready
format. Submissions in electronic form are prefered. Authors should
follow the IJCAI format. <http://www.ijcai.org/ijcai-97/CfX/cfp.html>
Review Process
--------------
Papers will be subject to peer review. Selection criteria include
accuracy and originality of ideas, clarity and significance of results
and the quality of the presentation.
The decision of the Program Committee, taking into consideration the
individual reviews, will be final and cannot be appealed. Papers
selected will be scheduled for presentation. Authors of accepted
papers, or their representatives, are expected to present their papers
at the conference.
Submission
----------
Electronic submission should be sent at zajac@crl.nmsu.edu. The
subject line should contain "IJCAI97 workshop submission". Papers
should be sent at the following address:
Rimi Zajac / IJCAI-97
Computing Research Laboratory
New-Mexico State University
PO Box 30001 / 3CRL
Las Cruces NM 88003
USA
Fax: +1-505-646-6218
Schedule
========
- March 15, 1997: Deadline for reception of submissions.
- May 1, 1997: Notification of acceptance.
- July 1, 1997: Deadline for reception of camera-ready copy.
- July 21, 1997: Publication of final list of workshop participants.
- August 23-25, 1997: IJCAI-97 Workshop.
Organizing Committee
====================
Rimi Zajac, CRL, New-Mexico State University, USA (Chair): zajac@crl.nmsu.edu
Lynn Carlson, US Department of Defense: lmcarls@afterlife.ncsc.mil
Kavi Mahesh, CRL, New-Mexico State University, USA: mahesh@crl.nmsu.edu
Kazunori Muraki, NEC, Japan: k-muraki@hum.cl.nec.co.jp
Nicholas Ostler, Linguacubun, Ltd., UK: nostler@chibcha.demon.co.uk
-------------------------------------------------------------------------------