LINGUIST List 8.551

Sun Apr 20 1997

Confs: 35th Annual Meeting of ACL

Editor for this issue: Ljuba Veselinova <>

We'd appreciate your limiting conference announcements to 150 lines, so that we can post more than 1 per issue. Please consider omitting information useful only to attendees, such as information on housing, transportation, or rooms and times of sessions. Please do not use abbreviations or acronyms for your conference unless you explain them in your text. Many people outside your area of specialization will not recognize them. Thank you for your cooperation.


  1. Priscilla Rasmussen, ACL97/EACL97 REGISTRATION BROCHURE


Date: Fri, 18 Apr 97 12:10:31 EDT
From: Priscilla Rasmussen <>


 			 7-12 July 1997
 	 Universidad Nacional de Educacion a Distancia
 			 Madrid, Spain


	 Rational Agency as the Basis for Natural Dialogue:
		 The ARTIMIS Technology
	 Dr. David Sadek, CNET, France Telecom, Lannion

 Current and Future EU Activities in the Field of Language Technologies
		 Mr. Nino Varile, European Commission


 		 ACL Business Meeting
 		 Student Member Lunch Meeting


 		 Program information
 		 Tutorial descriptions
 		 Post-conference workshops
 		 Student session information
 		Registration information and directions
 		 Accommodation information
 		 Application for preregistration
 		 Applications for accommodation

	(Each of these topics is seperated by a line of *****
	 and headed by the title listed here so you can search
	 for topics in the enclosed text.)



Tutorial Registration 		7:00PM-9:00PM
 Edificio de Humanidades, UNED, c/ Senda del Rey s/n
Tutorial Reception 		7:00PM-9:00PM
 Edificio de Humanidades, UNED, c/ Senda del Rey s/n

Tutorial Registration			8:00AM-1:00PM
Morning Tutorials:
 Machine Learning of Natural		9:00AM-1:00PM
 David Powers
 Information Retrieval from a		9:00AM-1:00PM
 Linguist's Perspective
 Sebastian Goeser and Gerda Ruge
Lunch					1:00PM-3:00PM
Afternoon Tutorials:
 Maximum Entropy Modeling		3:00PM-7:00PM
 for Natural Language
 Eric Sven Ristad
 Logical Approaches to Syntactic	3:00PM-7:00PM
 James Rogers and Thomas Cornell
 Conference Registration		3:00PM-8:00PM
 Edificio de Humanidades, UNED, c/Senda del Rey s/n
 Conference Reception			7:00PM-10:00PM
 Patio del Colegio Mayor Santa Teresa (nearby registration)
		 (Talks Are 30 Minutes)
Registration				8:00AM - 2:00PM & 3:00PM - 7:00PM
 (Tuesday-Friday) Edificio de Humanidades, UNED		
Parsing 			9:00AM - 10:30AM
 Interleaving Universal Principles and Relational Constraints over Typed
 Feature Logic
 Thilo Goetz and Detmar Meurers
 Fast Context-Free Parsing Requires Fast Boolean Matrix Multiplication
 Lillian Lee
 Three Generative, Lexicalised Models for Statistical Parsing
 Michael Collins
Text Classification 	9:00AM - 10:30AM
 Expansion of Multi-word Terms for Indexing and Retrieval Using Morphology
 and Syntax
 Christian Jacquemin, Judith Klavans, and Evelyne Tzoukermann
 Automatic Detection of Text Genre
 Brett Kessler, Geoff Nunberg, and Hinrich Schutze
 Document Classification Using A Finite Mixture Model
 Hang Li
Break		 	 		10:30AM - 11:00AM
Word Sense
Disambiguation 		11:00AM - 1:00 PM
 Combining Unsupervised LexicalKnowledge Methods for Word Sense
 G.Rigau, J. Atserias and E. Agirre
 Similarity-Based Methods for Word Sense Disambiguation
 Ido Dagan, Lillian Lee, and Fernando Pereira
 Using Syntactic Dependency as Local Context to Resolve Word Sense Ambiguity
 Dekang Lin
 Homonymy and Polysemy in Information Retrieval
 Robert Krovetz
Discourse 			11:00AM - 1:00 PM
 Learning Features that Predict Cue Usage
 Barbara Di Eugenio and Johanna D. Moore
 Expectations in Incremental Discourse Processing
 Dan Cristea and Bonnie Webber
 The Rhetorical Parsing of Unrestricted Natural Language Texts
 Daniel Marcu
 Centered Segmentation: Scaling up the Centering Model to Global Discourse
 Udo Hahn and Michael Strube
Lunch					1:00PM - 3:00PM
Practical Aspects of
Machine Translation	 		3:00PM - 4:30PM
 Probing the Lexicon in Evaluating Commercial MT Systems
 Martin Volk
 Ambiguity Resolution for Machine Translation of Telegraphic Messages
 Young-Suk Lee, Clifford Weinstein, Stephanie Seneff and Dinesh Tummala
 Machine Transliteration
 Kevin Knight and Jonathan Graehl
Lexicon 		3:00PM - 4:30 PM
 Intergrating Symbolic and Statistical Representations: The Lexicon
 Pragmatics Interface
 Ann Copestake and Alex Lascarides
 Negative Polarity Licensing at the Syntax-Semantics Interface
 John Fry
 Deriving Verbal and Compositonal Lexical Aspect for NLP Applications
 Bonnie Dorr and Mari Olsen
 Break					4:30PM - 5:00PM
Statistics and Meaning 		5:00PM - 6:30PM
 A DOP Model for Semantic Interpretation
 Rens Bod, Remko Bonnema and Remko Scha
 Fertility Models for Statistical Natural Language Understanding
 Mark Epstein, Salim Roukos, Todd Ward, and Stephen Della Pietra
 Predicting the Semantic Orientation of Adjectives
 Vasileios Hatzivassiloglou and Kathleen R. McKeown
Generation 		5:00PM - 7:00PM
 Discourse Segmentation and Reference Choices for Argumentative Texts
 Xiaorong Huang
 Sentence Planning as Description Using Tree Adjoining Grammar
 Matthew Stone and Christine Doran
 An algorithm for Generating Referential Descriptions with Flexible
 Helmut Horacek
 Applying Explanation-based Learning to Controlling and Speeding-up Natural
 Language Generation
 Guenter Neumann
		(Talks Are 30 Minutes Except Invited Talk;
		 Student Session 1 & 2 talks are under 20 minutes)
 INVITED TALK			 		9:00AM - 10:15AM
 Rational Agency as the Basis for Natural Dialogue: The ARTIMIS Technology
 Dr. David Sadek
 Break 			10:15AM - 11:00AM
Disambiguation		 			11:00AM - 1:00PM
 Independence Assumptions Considered Harmful
 Alexander Franz
 Mistake-Driven Mixture of Hierarchical Tag Context Trees
 Masahiko Haruno and Yuji Matsumoto
 A Flexible POS Tagger Using an Automatically Acquired Language Model
 Lluis Marquez and Lluis Padro
 Comparing a Linguistic and a Stochastic Tagger
 Christer Samuelsson and Atro Voutilainen
 Morphological Disambiguation by Voting Constraints
 Kemal Oflazer and Gokhan Tur
Spoken and Multimodal
Interaction		 			11:00AM - 1:00PM
 Intonational Boundaries, Speech Repairs, and Discourse Markers:
 Modeling Spoken Dialog
 Peter A. Heeman and James F. Allen
 Tracking Initiative in Collaborative Dialogue Interactions
 Jennifer Chu-Carroll and Michael K. Brown
 A Framework for Evaluating Spoken Dialogue Agents
 M. Walker, D. Litman, C. Kamm, and A. Abella
 Unification-based Multimodal Integration
 Michael Johnston, Philip R. Cohen, David McGee, Sharon L. Oviatt,
 James A. Pittman, and Ira Smith
Student Session 1 		 		11:00AM - 12:30PM
 A Structured Language Model
 Ciprian Chelba
 Incorporating Context Information for the Extraction of Terms
 Katerina Frantzi
 Knowledge Acquisition from Texts: Using an Automatic Clustering Method
 Based on Noun-Modifier Relationship
 Houssem Assadi
 Choosing the Word Most Typical in Context Using a Lexical Co-occurrence
 Philip Edmonds
 Improving Translation through Contextual Information
 Maite Taboada
Lunch 		1:00PM - 3:00PM
Finite State Technologies	 		3:00PM - 4:30PM
 Efficient Generation in Primitive Optimality Theory Using Factored Automata
 Jason Eisner
 A Trainable Rule-Based Algorithm for Word Segmentation
 David D. Palmer
 Compiling Regular Formalisms with Rule Features into Finite-State Automata
 George Anton Kiraz
Statistical Machine
Translation 		 			3:00PM - 4:30PM
 A DP-based Search Using Monotone Alignments in Statistical Translation
 C. Tillmann, S. Vogel, H. Ney and A. Zubiaga
 An Alignment Method for Noisy Parallel Corpora Based on Image Processing
 Jason J.S. Chang and Mathis H. Chen
 A Portable Algorithm for Mapping Bitext Correspondence
 I. Dan Melamed
Student Session 2				3:00PM - 4:30PM
 Generative Power of CCGs with Generalized Type-Raised Categories
 Nobo Komagata
 Representing Paraphrases Using Synchronous Tree Adjoining Grammars
 Mark Dras
 Contrastive accent in a data-to-speech system
 Mariet Theune
 Towards resolution of bridging descriptions
 Renata Vieira and Simone Teufel
 Modelling the Semantics of German Verb Prefixes
 Maria Wolters
 Break						4:30PM - 5:00PM
 Syntax and Morphology 	 		5:00PM - 6:30PM
 The Complexity of Recognition of Linguistically Adequate Dependency Grammars
 Peter Neuhaus and Norbert Broker
 Maximal Incrementality in Linear Categorial Deduction
 Mark Hepple
 Automatic Extraction of Aaspectual Information from a Monolingual Corpus
 Akira Oishi and Yuji Matsumoto
Machine Translation and
Language Modeling				5:00PM - 7:00PM
 A Comparison of Head Transducers and Transfer for a Limited Domain
 Translation Application
 Hiyan Alshawi, Adam L. Buchsbaum, and Fei Xia
 Decoding Algorithm in Statistical Machine Translation
 Ye-Yi Wang
 Accounting for Distance in a Long-range Language Model
 Adam Berger and John Lafferty
 Hierarchical Non-Emitting Markov Models
 Eric Ristad and Robert Thomas

		 (Talks Are 30 Minutes, Except Invited Talk)
INVITED TALK					9:00AM - 10:15AM
 Current and Future EU Activities in the Field of Language Technologies
 Mr. Nino Varile
Break 		10:15AM - 11:00AM
and Parallelism 				11:00AM - 1:00PM
 Efficient Construction of Underspecified Semantics under Massive Ambiguity
 Jochen Dorre
 A Theory of Parallelism and the Case of VP Ellipsis
 Jerry R. Hobbs and Andrew Kehler
 On Interpreting F-structures as UDRSS
 J. van Genabith and Richard Crouch
 A Uniform Approach to Underspecification and Parallelism
 Joachim Niehren, Manfred Pinkal, and Peter Ruhrberg
Learning, Analogy,
and Evolution 		 			11:00AM - 1:00PM
 Co-Evolution of Language and of the Language Acquisition Device
 Ted Briscoe
 Paradigmatic Cascades: A Linguistically Sound Model of Pronunciation by
 Francois Yvon
 Memory-Based Learning: Using Similarity for Smoothing
 Jokub Zavrel and Walter Daelemans
 String Transformation Learning
 Giorgio Satta and John C. Henderson
Lunch						1:00PM - 3:00PM
ACL Business Meeting 				3:00PM - 4:30PM
Break 	 		4:30PM - 5:00PM
Finite State
Approximation 		 		5:00PM - 6:30 PM
 Approximating Context-Free Grammars with a Finite-State Calculus
 Edmund Grimley Evans
 Finite State Transducers Approximating Hidden Markov Models
 Andre Kempe
 Compactly Representing Constraints with Automata
 Frank Morawietz and Tom Cornell
Machine Translation 		 		5:00PM - 6:30PM
 Retrieving Collocations by Co-Occurences and Word Order Constraints
 Sayori Shimohata, Toshiyuki Sugio, and Junji Nagata
 Learning Parse and Translation Decisions from Examples with Rich Context
 Ulf Hermjakob and Raymond J. Mooney
 A Word-to-Word Model of Translational Equivalence
 I. Dan Melamed


A full listing of the Program Committee can be found in the
ACL97/EACL97 Proceedings. Included here are the Program and
Area Chairs only: 
Philip Cohen (Oregon Graduate Institute), Program Co-Chair; 
Wolfgang Wahlster (DFKI, GmbH), Program Co-Chair; 

Donia Scott (University of Rochester) Area Chair: Semantics,
	Pragmatics, and Discourse;

Eugene Charniak (Brown University), Area Chair: Statistical
	Language Processing;

Koenraad de Smedt (University of Bergen), Area Chair: Grammar,
	Formalisms for Parsing and Tactical Generation; 

Elisabeth Andre, Area Chair: Uses of Language Processing;

Lauri Kartunnen (RXRC Rank-Xerox), Area Chair: Morphology,
	Lexicon, and Finite State Technology.


Students: P amela W. Jordan (University of Pittsburgh, co-chair),
Johan Bos (University of the Saarland, co-chair), Paul Buitelaar
(Brandeis University), Alastair Butler (University of East Anglia),
Bekki Daisuke (University of Tokyo), Mariana Damova (University of
Stuttgart), Eric Fosler (U.C. Berkeley), Rob Koeling (University of
Groningen), Mark Lee (University of Sheffield), Maria Milosavljevic
(Macquarie University), Ted Pedersen (Southern Methodist University),
Carolyn Rose (Carnegie Mellon University), Bilge Say (Bilkent University),
Michael Schiehlen (University of Stuttgart), Hadar Shemtov (Stanford
University), B. Srinivas (University of Pennsylvania), Kjetil Strand
(University of Oslo), David Tugwell (University of Edinburgh), Peter
Vanderheyden (University of Waterloo).
Non-students: W. Scott Bennett (Logos Corp.), Martin Emele (University
of Stuttgart), Ted Gibson (Massachusetts Institute of Technology),
Paola Merlo (University of Geneva), Marie Meteer (BBN), Susan McRoy
(University of Wisconsin-Milwaukee), Massimo Poesio (University of
Edinburgh), Craige Roberts (Ohio State University), Patrick Saint-Dizier
(Institut de Recherche en Informatique Toulouse), Koichi Takeda (Tokyo
Research Laboratory, IBM Japan), Gertjan vanNoord (University of Groningen).
Additional Reviewers: Kathryn Baker (Carnegie Mellon University), Bianka
Buschbeck (University of Stuttgart), Matthew Stone (University of
Pennsylvania), Nancy Green, Carnegie Mellon University), Mark-Jan Nederhof
(University of Groningen).


		 Monday 7 July 1997, 9:30AM--6:30PM

 	 Machine Learning of Natural Language, 9:30AM--1:00PM

 	David Powers, The Flinders University of South Australia

Over the last 30 years, issues relating to how language can be learned
have shaped fields as diverse as linguistics, automata theory, and
psycholinguistics. More recently, machine learning and neural nets
have found linguistic problems a natural target for exploration and
demonstration of techniques. Conversely, computational linguistics,
natural language processing and speech technology are all actively
looking for ways in which learning can be put to practical use in
specific applications. Indeed, the increasing availability of large
corpora and treebanks promises that the recent explosion in interest
will continue.

This tutorial will provide the participant with an understanding of
the perspectives on language learning adopted by the different fields,
will explore the nature and significance of the various theoretical
results, and will characterize and explain the basic machine learning
paradigms and algorithms which have been used for language learning.
Recent work will be characterized in terms of this framework, with
more detailed case studies being drawn from two different paradigms.
The focus here will be on developing an intuition as to how and why
the various techniques work.

David Powers is co-author of the Springer monograph 'Machine Learning
of Natural Language' and is currently President of SIGNLL, the ACL
Special Interest Group on Natural Language Learning. This tutorial
will provide background useful to those contemplating attending
SIGNLL's two day CoNLL workshop.

 Information Retrieval from a Linguist's Perspective, 9:30AM--1:00PM

 		Sebastian Goeser, IBM Germany Ltd.
	 Gerda Ruge, Technical University of Munich

Information Retrieval (IR) is a dynamically growing field of research
and development activities which offers many substantial job
opportunities to linguists. The purpose of this tutorial is to
introduce computational or theoretical linguists to IR, thus enabling
them to make reasonable decisions on linguistic issues in an IR
context. The tutorial will give an overview of all major issues in IR
research and development that are relevant to a linguist in that

An important focus will be the effectiveness of linguistic
approaches to IR: Which methods are provably effective, and which
ones, in spite of arguments to the contrary, are not? The literature
on linguistic IR experiments reports many conflicting results. The IR
community is split into those who believe language technology can
improve retrieval results and those who do not. The entire IR
machinery necessary to understand this situation, in terms of
retrieval models, evaluation, system architectures, applications,
linguistic representation etc. will be focused in this tutorial.


 		Eric Sven Ristad, Princeton University

The maximum entropy framework is a powerful method for building
statistical models of natural language. It is expressive, allowing
modelers to easily represent their special insights into the data
generating machinery. It is statistically efficient, because it
models the intersection of complex events without increasing the
number of parameters or fragmenting the training data. And it
provides strong models, models that can outperform their traditional
variants with less tweaking.

This tutorial explains how to build maximum entropy models for natural
language applications such as information retrieval and speech
recognition. We review the maximum entropy framework, explore the art
of effective feature design, and show how to implement models using
the instructor's publicly available Maximum Entropy Modeling

 Logical Approaches to Syntactic Theories, 3:00PM--6:30PM

 	 James Rogers, University of Central Florida
	Thomas Cornell, SFB 340, University of Tuebingen

The trend, over the last ten or fifteen years, has been towards
specifying syntactic structures in terms of constraints on their form
rather than via mechanisms for generating them. This leads naturally
to a fully declarative approach in which sets of syntactic structures
are treated as sets of ordinary mathematical models and theories of
syntax are defined by systems of logical axioms. This model-theoretic
approach allows existing tools of mathematical logic to be applied to
formal issues in syntax. In addition to the obvious applications to
questions of consistency and independence of sets of constraints,
results have been obtained establishing the complexity of constraint
based theories, logical axiomatizations have been employed as a common
framework in which to compare strongly dissimilar generative systems,
and automata-based proof techniques have begun to be explored as novel
approaches to processing languages axiomatized in this way. This
tutorial will explore the foundations of this approach, the results it
has yielded so far, and the potential it holds.

The presentation will presume only a passing familiarity with basic
formal logic and traditional theories of syntax (e.g., GB and GPSG).


 	Natural Language Processing for Communication Aids
 Organisers: Ann Copestake (Stanford University), Stefan Langer
 (University of Dundee), and Sira E. Palazuelos-Cagigas
 (Universidad Politecnica de Madrid).
 July 11 or 12, 1997
The aim of this workshop is to provide a forum in which researchers in
communication aids for people with disabilities can discuss the problems
involved in these applications and the solutions being investigated in current
research. Researchers who are not currently working in this area but who are
interested in practical uses for NLP techniques are also encouraged to
participate. Applications which we expect to be covered include communication
devices for non-speakers, systems designed for deaf users and tools for
tutoring and rehabilitation for people with language impairments. Those
interested in attending should contact Ann Copestake (
For further details of the workshop see

		 SIGPHON: Computational Phonology
 July 11 or 12, 1997

 		 Concept to Speech Generation Systems
 Organisers: Kai Alter and Hannes Pirker (Austrian Research Inst. for
		AI) and Wolfgang Finkler (German Research Center for AI).
Friday, July 11, 1997

This workshop deals with Concept-to-Speech (CTS) generation systems, i. e.,
the production of synthetic speech on the basis of semantic, discourse,
phonological and phonetic knowledge. It will thus provide a forum to bring
together researchers from the fields of natural language generation and speech
synthesis. The aim of the workshop is to stimulate interchange of innovative
ideas and results of diverse aspects of CTS generaation and should be
especially attractive for people who are interested in language generation and
prosody. More detailed information including the program can be retrieved at The organising
committee can be contacted at

 			Spoken Language Translation
 Organisers: Steven Krauwer (Utrecht University; ELSNET, chair), Harold
	 Somers (UMIST; Machine Translation), Doug Arnold (University of
	 Essex), Walter Kasper (DFKI Saarbruecken), Manny Rayner (SRI
 July 11, 1997

The workshop will be dedicated to spoken language translation (SLT), and its
interrelationships with machine translation of written language (MT). It will
be a one-day workshop, with four consecutive sessions, addressing the following
four issues: current trends in SLT research (approaches, problems); current
trends in SLT applications (products, niches); how / where can MT and SLT learn
from each other; what can be done to improve convergence or synergy. Contact: Details:

 		 Envgram Computational Environments for
		Grammar Development and Linguistic Engineering
 Organizers: Dominique Estival (University of Melbourne, Australia),
	Alberto Labelli (IRST), Klays Netter (DFKI), and Fabio Pianesi (IRST)
 July 11 or 12, 1997

With a growing number of NLP applications going beyond the status of simple
research systems, there is also an evident need for better methods, tools and
environments to support the development and reuse of large scale linguistic
resources and efficient processors. However, while current platforms and
components typically provide fairly clean formalisms, processing components and
data, it is not yet clear to which extent current results and approaches fit
the requirements for scale development and deployment of real NLP applications.
Among the relevant issues, we mention: the assessment of the state of the art
grammar development and to the division of labor in large scale grammar
development; the problems of the reusablility (of linguistic resources and / or
processors) and of the usability (from the point of view of the user of the
platform). This workshop intends to provide a forum for discussing these and
related, crucial issues for Linguistic Engineering.

 		Operational Factors in Practical, Robust
	 Anaphora Resolution for Unrestricted Texts
 Organisers: Ruslan Mitkob (University of Wolverhampton, UK, e-mail: and Branimir Boguraev (Apple Computer,
	 Inc. Cupertino, CA, USA).
 July 11, 1997

The workshop will have a dual focus: it will promote the latest trends towards
robust, parser-free, corpus-driven and / or other practical approaches to
resolving anaphora in unrestricted texts; it will also seek to investigate the
role of, and interactions among, the various factors in anaphora resolution and
in particular those that scale well in knowledge-poor environments.

 		 Interactive Spoken Dialogue Systems:
	 Bringing Speech and NLP Together in Real Applications
 Organisers: Julia Hirschberg, Candace Kamm, and Marilyn Walker
	 (ATT Labs Research).
 July 11 and 12, 1997

Recent advances in speech technologies, natural language processing, and
dialogue modeling have made it possible to build dialogue agents for a wide
range of applications from voice dialing to accessing information about the
weather, train schedules, cultural events or local restaurants. However, there
is little research on the integration of component technologies required for
these agents. This two-day workshop will address the challenges involved in
this integration, including the special requirements dialogue places on speech
recognizers, speech synthesizers and natural language generation; tools for
building integrated systems; and evaluation of spoken dialogue systems. The
workshop will begin with a morning of tutorials on ASR, TTS, and dialogue
modeling. We solicit participation from text-to-speech, ASR, NLP, generation
and dialogue modeling researchers, as well as those already building integrated
spoken dialogue systems.

	 Referring Phenomena in a Multimedia Discourse
	 and Their Computational Treatment (SIGMEDIA)
 Organisers: Elisabeth Andre (DFKI, Germany), Laurent Romary (CRIN-CNRS
	& INRIA Lorraine, France), and Thomas Rist (DFKI, Germany)
	 Organized by the ACL Special Interest Group
	 on Multimedia Language Processing (SIGMEDIA)
 July 11th/12th 1997

A growing number of research projects has started to investigate the
use of referring expressions in multimedia systems. On the one hand,
the use of multiple media has led to new problems, such as a proper
treatment of cross-media references. On the other hand, it has turned
out that many concepts already known from natural language processing,
such as cohesion, take on an extended meaning in multimedia
discourse. As theories of NL reference become more sophisticated, it
is quite natural to investigate whether these theories also encompass
other media, such as graphics and pointing gestures. The workshop will
be centered around questions, such as "To what extent can linguistic
models be applied to multimedia references?", "Which linguistic
phenomena can also be observed in multimedia discourse?" and "Is a
cross-modality theory of reference possible?". Topics of interest
include, but are by no means restricted to the following:

- computational models for the analysis/generation of referring
 expressions in a multimedia discourse
- coordination/synchronization of multiple media, such as speech and
 pointing gestures
- deixis in multimedia environments
- cohesion and coherence in multimedia discourse
- representation of multimedia discourse
- encoding theories for text and graphics
- formal models of multimedia referring
- referring expressions in augmented/virtual realities
- empirical studies

Contacts: Elisabeth Andre, email:; Laurent Romary,
email:; Thomas Rist, email:

 		 Intelligent Scalable Text Summarization
 Organisers: Udo Hahn (University of Freiburg), Julian Kupiec (Xerox
	PARC), Inderjeet Mani (MITRE, co-chair), Mark Maybury (MITRE,
	co-chair), Kathy McKeown (Columbia University), Boyan Onyshkevych
	(US Department of Defense), Dragomir Radev (Columbia University),
	Lisa Rau (SRA International), and Kazuo Tanaka (NTT Human Interface
 Friday, July 11, 1997

With the explosion in the quantity of on-line information in recent years,
demand for text summarization technology appears to be growing. Commercial
companies are increasingly starting to offer text summarization capabilities,
often bundled with information retrieval tools. These recent developments
offer opportunities as well as substantial challenges for research in text
summarization. In general, such developments create a practical need for
summarization systems which scale up when applied to large volumes of
unrestricted text. This workshop is aimed at researchers interested in
advancing the scientific frontiers of text summarization to meet these new
practical challenges and opportunities. For further information, see

 Automatic Information Extraction and Building of Lexical
	Semantic Resources for NLP Applications Organized by
 EuroWordNet (LE2 4003), Sparkle (LE1 2111) and Ecran
 Organisers: Piek Vossen (University of Amsterdam), Nicoletta Calzolari
	(Instituto de Linguistica Computazionale del CNR, Pisa), Yorick
	Wilks (University of Sheffield), Geert Adriaens (Novell Linguistic
	Development, Antwerp), and Horacio Rodriquez (Politecnica de
	Catalunya, Barcelona).
 Friday, July 11, 1997

In the past years the development of high-quality and overall language
resources has been the focus of many research groups. More recently also
the corpus-based extraction of such resources has gained a wider interest.
EuroWordNet, Sparkle and Ecran try to package some of this know-how and
expertise into state-of-the-art tools and resources that can directly be
applied in NLP-based services. This objective is carried out through the
development of software tools in the areas of shallow parsing and lexical
acquisition. These tools are used to induce linguistic knowledge from text
corpora and are progressively enriched by the information acquired.
In this workshop we want to discuss the scope and formats of semantic resources
and information acquisition tools with scholars in the field and researchers
from commercial R departments who have experience in developing and using
them. Specifically we will discuss the following topics: 1. compatibility and
standards of multilingual semantic resources and lexical acquisition tools; 2.
the validation of multilingual semantic resources and lexical acquisition
tools; 3. performances of semantic resources and lexical acquisition tools in
NLP tasks; 4. partial or phrasal parsing of text; 5. linking text with lexical
databases: sense-differentiation, sense-tagging and sense-disambiguation tasks,
domain-differentiation of text and lexical resources. Further details can be
found at the Workshop HomePage:

 		From Research to Commercial Applications:
		 Making NLP Technology Work in Practice
 Organisers: Jill Burstein (Educational Testing Service), Claudia Leacock
	(Princeton University), Jared Bernstein (Ordinate Corporation),
	Andrew Golding (Mitsubishi Electric), Mary Dee Harris (Language
	Technology, Inc.), Kevin Knight (USC / ISI), Karen Kukich (Bellcore),
	Lisa Rau (SRA International), Yael Ravin (IBM, T. J. Watson Research
	Center) Susanne Wolff (Educational Testing Service), and Wlodek
	Zadrozny (IBM, T. J. Watson Research Center).
 JUly 11 or 12, 1997

Success in the marketplace is one form of validation for NLP techniques and
underlying theories. The broad vision of this workshop is to bring together
researchers to discuss commercial or commercial-bound systems that use NLP for
either text or speech. We are interested in learning about systems that show
promise in re-using NLP techniques, and in the process of technology transfer
for NLP applications. Another topic of interest in this workshop is
industry-based practical considerations involving NLP technology. The workshop
should invoke discussion about experiences and problems -- technical, logistic,
or cultural -- among people working on operational and commercial NLP
applications. The workshop will begin a dialogue among researchers to explore
issues in technology transfer and the re-use of domain-specific systems.
Discussion of the issues above would help to create connections between both
academic and industry-based research efforts to build a solid infrastructure
for NLP technology re-use and lead to a deeper understanding of commercial NLP

 	 Computational Natural Language Learning (CoNLL '97)
 Organisers: Mark Ellison (Edinburgh University), David Powers (Flinders
	University), and Walter Daelemans (KUB Tilburg, Antwerp University)
 July 11 or 12, 1997

The field of computational natural language learning (NLL) is not a new one;
research in it has been pursued for more than forty years. The last seven
years, however, have seen a growth in interest and, correspondingly, in
meetings addressing this topic. These have been held under the auspices of:
COLING (The Unfinished Language, 90), DARPA (90/91), AAAI (MLNLO/CNLP, 91/93),
IJCAI (NLL, 91), ECML (Machine Learning and Text Analysis, 93), the European
Networks of Excellence ELSNET and MLNET (MLNLS, 94), and ESSLLI (96).
This year, however, is the first time the that the ACL's special interest group
in natural language learning have organised a meeting in conjunction with an
(E)ACL conference. This as an important event for researchers in NLL for two
reasons. The meeting will provide a venue to share work on our common interests
within the NLL community. Secondly, it provides the opportunity for the wider
ACL community to become acquainted with NLL work.

For these reasons, we are soliciting for papers from the full breadth of NLL
research. This includes work aimed at using machines to learn linguistic
models, building computational models of language, and natural language tool
development and adaptation. Our coverage explicitly extends to work using
probabilistic, symbolic and neural network learning methods, and to the
computational modelling of language acquisition. We make no restrictions on the
target of acquisition, including work on all levels of language from semantics
and pragmatics, through syntax and the lexicon to phonology and phonetics. All
submissions will be subjected to blind refereeing by appropriate experts.
The combination of this vibrant field, with the occasion of joint EACL/ACL
meeting will make this workshop an exciting and stimulating event.


Registrations via email to are strongly preferred. Please
note that the cutoff date for pre-registration is May 31 .

Registration fees are US $60 for 1 day workshops and US $80 for 2 day
workshops. Workshop attendees must be registered for the conference.
Acceptable forms of payment are cheques in US dollars payable to ``ACL''
or credit card (VISA/Mastercard) payment. Please submit the following form
with payment indicating the workshop you are interested in.


Institution: (for name tag)______________________________________________

Postal Address:__________________________________________________________


Phone and Fax:___________________________________________________________

Name of Workshops (Circle or check the one(s) you plan to attend):

Natural Language Processing for Communication Aids
SIGPHON: Computational Phonology
Concept to Speech Generation Systems
Spoken Language Translation
Envgram Computational Environments for Grammar Development and Linguistic
Operational Factors in Practical, Robust Anaphora Resolution for
	Unrestricted Texts
Interactive Spoken Dialogue Systems: Bringing Speech and NLP Together
	in Real World Applications
SIGMEDIA: Referring Phenomena in a Multimedia Discourse and Their
	Computational Treatment
Intelligent Scalable Text Summarization
Automatic Information Extraction and Building of Lexical Semantic Resources
	for NLP Applications Organized by EuroWordNet (LE2 4003), Sparkle
	(LE 2111) and Ecran
>From Research to Commercial Applications: Making NLP Technology Work
	in Practice
Computational Natural Language Learning (CoNLL '97)

Payment: specify cheque or credit card
Credit card type: (Visa/Mastercard only)________________________________
Credit card info:
name on card, 		card number, 				expir date
Dietary requirements: vegetarian, etc.

 Please send to:

 Priscilla Rasmussen 		phone: +1-908-873-3898
 P. O. Box 6090			fax: +1-908-873-0014
 Somerset, NJ 08875, USA		email:



 Technical Program: Tuesday-Thursday, July 8-10.
 Tutorials: Monday, July 7.
 Post-conference Workshops: Friday-Saturday July 11-12.

For this information and further details about ACL/EACL-97 and the
UNED area, see the WWW page:
also accessible from the ACL home page:

preregistration form and send it with payment to ``Association for
Computational Linguistics'' or ``ACL'' to ACL, P.O. Box 6090,
Somerset, NJ 08875 USA, email:, 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.

Registration will take place at the Edificio de Humanidades, UNED,
c/ Senda del Rey s/n.

SITE: ACL/EACL-97 will be held at the UNED (Universidad Nacional
de Educacion a Distancia), Madrid.

TUTORIALS: Four tutorials will be held the day before the conference,
Monday, July 7. Attendance in each tutorial is limited. Preregistration
is essential to ensure a place and guarantee that syllabus materials
will be available. Registration will take place at the Edificio de
Humanidades, UNED, c/ Senda del Rey s/n.

TUTORIAL RECEPTION: Reception and a cash bar for tutorial attendees
will be held on Sunday evening, July 6, at the Edificio de Humanidades,
UNED, c/ Senda del Rey s/n.

OPENING RECEPTION: The opening reception will be held on Monday evening,
July 7, at the Patio del Colegio Mayor Santa Teresa (near the registration

BANQUET: The conference banquet will be held on Wednesday evening,
July 9. Mitch Marcus will deliver the Presidential Address.

STUDENT LUNCH: On Thursday, the ACL is hosting a complimentary lunch
meeting for ACL student members and for regular members who qualify as
students, to allow them to discuss the student sessions and to plan for
the next meeting. Please check the box on the registration form if you
are a student and wish to participate in the student lunch session.

BUSINESS MEETING: The annual ACL business meeting will be held on
Thursday, July 10. The business meeting will include discussion of
possible changes in conferences and organizational structure of the
ACL. Nominations for ACL offices for 1997: President: Eva Hajicova,
Univ. of Prague; Vice President: Phil Cohen, Oregon Graduate
Institute. Executive Committee (1997-99): Steven Pullman, Cambridge
University; Nominating Committee (1997-99): Mitch Marcus, Univ. of

LOCAL ORGANIZING COMMITTEE: Chair: Maria Felisa Verdejo (Universidad
Nacional de Educacion a Distancia), Alfredo Fernandez-Valmayor (Universidad
Complutense de Madrid), Ana Garcia Serrano (Universidad Politecnica de Madrid),
Jose Carlos Gonzolez (Universidad Politecnica de Madrid), Julio Gonzalo
(Universidad Nacional de Educacion a Distancia), Julia Lavid (Universidad
Complutense de Madrid), Joaquim Llisterri (Instituto Cervantes), Victoria
Marrero (Universidad Nacional de Educacion a Distancia), Fernando Sanchez
Leon (Laboratorio de Linguistica Informatica), Universidad Autonoma de
Madrid), Luis de Sopena (IBM Espana), Manuel Palomar (President of the
Sociedad Espanola para el Procesamiento del Lenguaje Natural).

LOCAL ARRANGEMENTS: Specific inquiries regarding on-campus apartment
accommodation may be directed to the FUE Conference Office via fax at
+34 1-547 06 52 and sent to the attention of Marisol Pastor; An
application form for housing registration is enclosed. For other
local arrangements questions contact

EXHIBITS AND DEMONSTRATIONS: A number of publisher exhibits and computer
demonstrations have been scheduled. For information on arranging
demonstrations and exhibits mail For exhibits of
research systems, the charge is a nominal $60. The fee for exhibiting
a commercial system (intended for sale as a product) is $500.

SPONSORS: The organizers are most grateful to the European Commission,
the UNED (Universidad Nacional de Educacion a Distancia), the Autonoma
University, the Complutense University and the Politecnica University
of Madrid for the generous grants they have made to support the conference.

SMOKING POLICY: In Spain, in spite of a decrease in the number of
smokers, there are still a lot of people who smoke. Smoking is not
permitted in any room at the university but tolerated in other
designated public areas.

RECREATION: A variety of athletic facilities (with moderate fees)
are available on campus including a summer swimming pool. Athletic passes
will be available at the Registration desk.

GEOGRAPHIC SITUATION AND CLIMATE: Located in the center of the Iberian
Peninsula, Madrid is 600 m. above sea level. In mid July it is hot but dry,
the maximum can vary from 30 to 38 centigrade degrees. Short summer storms
in the evening are quite possible.

SIGHTSEEING: The capital of Spain, Madrid is filled with museums, beautiful
architecture, fascinating history and charming people that welcome strangers
with genuine zeal. From the streets packed with bustling people, to the quiet
dignity of a city that is over four-hundred years old, Madrid has much to
offer anyone who visits it.

Its forcefulness and personality turn Madrid into an unforgettable city,
and its plentiful resources of interest to tourism - nature, art,
history - are rounded off extraordinarily well by a series of cities in
its surroundings which are full of sights of historic interest, some of
which have been included by the UNESCO in the list of places considered
"world heritage": Avila, Segovia, Toledo, as well as the Monastery of El
Escorial. All of them lie within about 100 km. from the square La Puerta
del Sol.

Nearby the conference site is the American Museum were you can enjoy a
large collection of Central and South American objects belonging to a
variety of cultures. The Museum is within the campus Ciudad Universitaria
located at the intersection between the Avenida Arco de la Victoria and
the Avenida de los Reyes Catolicos. On the way from hotels to the university,
The Church of San Antonio de la Florida, which was declared a National
Monument in 1905, was built between 1792 and 1798, and Francisco de Goya's
frescoes are a tourist attraction in their own right.

Suitable attire is required for visiting churches.

DIRECTIONS: All air trafic passes through Barajas airport, 15 km. from
Madrid. To reach the city either you take the bus or a taxi because there
is no metro or fast train. Taxi rates and surcharges: Authorized taxis
are white with a red diagonal band on the door. Within the city, and
including the airport, the fare is the one indicated on the meter, plus
the authorized surcharges. Initial fare: 170 ptas., airport surcharge:
350 ptas., surcharge for night service (11:00pm-6:00am): 150 ptas., for
each suitcase: 50 ptas. An aproximate charge in normal traffic conditions
from the airport to Plaza de Espana would be between 2500 and 3000 ptas.
If you have any complaint, you can ask for a receipt but make sure it's
got the taxi's licence on it and the route taken. By bus: There is a
yellow bus at the airport wich leaves every 15 minutes and costs 370
pesetas. They do not accept big notes, so change in the airport before
taking the bus. The bus takes you to the terminal, in the city center
(Plaza de Colon/Columbus square) from where you can take the metro.

By car: Using a car in Madrid is not advisable because there is
heavy traffic and it is very difficult to park in the center of Madrid.
LOCAL DIRECTIONS: (From the hotels to the conference site): From the
hotels: Catch bus 46 at a bus stop in front of the conference hotels
(direction Moncloa) and it will take you straight to UNED in "Senda del
Rey" (conference site). This bus runs from 6:30am to 11:00pm. A single
ticket costs 130 ptas and you can pay on the bus, but we recommend you
get a bono-bus (10 trips) which costs 660 pesetas. This is sold at
"estancos" (tobacconists) and newspapers kiosks. If you are lodging
in the campus residence - Colegio Mayor Antonio de Nebrija- just
walk down the Avenida de Seneca and you'll get to the conference site.
There will be signs around the campus to help you find your way.

PARKING: Two of the three hotels have parking for a fee but as stated above
it is not advisable to drive in Madrid.

FOREIGN CURRENCY EXCHANGE: All bank branch offices offer foreign currency
exchange services, and although a considerable number of hotels and many
travel agencies do also, it's wiser to exchange your money at a bank office.
All banks are open from 8:30 to 2:00, 2:30 from Monday to Friday. If you
arrive on a Sunday there is a bank office open at the airport of Barajas.
Most hotels and restaurants and many commercial establishments also
accept the most popular international credit cards and travellers



HOTEL INFORMATION: There are three hotels on offer. All three are
downtown and the Hotel Florida Park is within walking distance from the
conference site (UNED). The hotels are: Espahotels Plaza de Espana,
Espahotel Gran Via 65, and Hotel Florida Park.

Espahotels Plaza de Espana: Located at Plaza de Espana,7.
Parking facilities located in the building, lift from the entrance hall.
Rooms with full bath, satellite TV (European channels), air conditioning,
music, minibar etc. The restaurant is open from 7:30 am to 12pm and the
cafeteria is also available for snacks. Prices (in Pesetas, followed by
US dollar equivalent as of 17 April 1997 but not guaranteed due to possible
currency conversion fluctuations): Single: 10.000 pesetas ($68.50), Double:
12.500 pesetas ($85.63).

Espahotel Gran Via 65: Located at Gran Via 65, just a few meters from Plaza
Espana. Rooms with full bath, satellite TV (European channels), air
conditioning, music, minibar etc. The restaurant is open from 7:30 am to
12pm and the cafeteria is also available for snacks. Prices (in Pesetas,
followed by US dollar equivalent as of 17 April 1997 but not guaranteed
due to possible currency conversion fluctuations): Single: 10.000 pesetas
($68.50), Double: 12.500 pesetas ($85.63).

Hotel Florida Park: Four star hotel located at Paseo de la Florida 5,
28008 Madrid, within 20 minutes walking distance from the conference
site. Garage, lift, money exchange, room service 24 hours, air conditioning,
telephone in rooms, satellite TV...Only a limited number of rooms could be
reserved at each hotel. Prices (in Pesetas, followed by US dollar equivalent
as of 17 April 1997 but not guaranteed due to possible currency conversion
fluctuations): Single: 9.000 pesetas ($61.65), Double: 11.000 pesetas

RESERVATIONS SHOULD BE MADE BY 31 MAY. Send the form below to Agencia del
Corte Ingles; fees do not stand if contacting directly to the hotels. Hotel
Florida Norte is 20 minutes walking from the conference site; there is
public transportation to all hotels.

Cancellation costs: until May 31: none; from May 31 to June 20: $20;
later, it will be applied $50.

ACL/EACL-97 Hotel Accomodation: The application form has to be sent by fax to:
Agencia de Viajes
El Corte Ingles
Fax (341)398 60 85

Accomodation will be guaranteed only if reserved before May 31.

HOUSING INFORMATION (on campus housing): You must send the housing
information form before MAY 30, 1997. Return by FAX to: Fundacion
Universidad Empresa/ Att. Soledad Pastor. Fax number: 34 1 5470652

ACL/EACL-97 has reserved a block of rooms at the Nebrija student
residence located within the university area and five minutes walking
distance from the conference site and university sport facilities
(swimming pool etc.). Accommodations include linen but no other facilities
such as towels, soap, hangers... The rooms do not have air conditioning but
the university area is not as hot as downtown in midsummer. Rates: full
board (including breakfast, lunch and dinner). Single room night/person
individual bathroom: 5.500 Spanish ptas (approx. $43). Single room
night/person shared bathroom: 4.500 Spanish ptas (approx. $35).

Deadlines: The deadline for housing reservation is May 30, 1997. We can
not guarantee any reservations after this deadline.

Reservations: Housing reservations will be processed on a first-come
first-served basis. ACL/EACL-97 will accept only written reservations
accompanied by payment in full.

Payment: Payment of housing fees is required. Bank check in pesetas payable
to Fundacion Universidad Empresa drawn on any Spanish bank for single rooms
without individual bathroom. VISA, MASTERCARD are accepted for both (individual
or shared bathrooms). Bank check must be sent to the following address:

Att:Soledad Pastor
Fundacion Universidad Empresa
c/ Serrano Jover, n5 p7
28015 Madrid, Spain

The deadline for refund requests is May 30, 1997. Refund requests must
be in writing.


 35th Annual Meeting of the Association for Computational Linguistics
		8th Conference of theEuropean Chapter of the
		 Association for Computational Linguistics
7-12 July 1997, Universidad Nacional de Educacion a Distancia, Madrid, Spain

NAME _______________________________________________________________________
		Last			First			Middle

ADDRESS ____________________________________________________________________

AFFILIATION (for badge) ____________________________________________________

TELEPHONE __________________________________________________________________

E-MAIL ADDRESS _____________________________________________________________

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.


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.

To attend two tutorials, pay twice the amount shown.

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:
[ ] Machine Learning of Natural Language
[ ] Information Retrieval from a Linguist's Perspective
 Monday afternoon tutorials -- select at most ONE:
[ ] Maximum Entropy Modeling for Natural Language
[ ] Logical Approaches to Syntactic Theories

BANQUET TICKETS ($50 each): $____________________

MEAL CHOICE: [ ] Vegetarian; [ ] Non-Vegetarian

STUDENT MEMBER LUNCH: [ ] Will attend [ ] Will not attend
 Note: only open to student members or regular members who are students.

EXTRA PROCEEDINGS for REGISTRANTS ($30 each): $__________________

PROCEEDINGS ONLY ($30 members; $60 others): $____________________
NOTE: there is no deadline for Proceedings Only orders (August 1997 delivery)

TOTAL PAYMENT --- MUST BE INCLUDED: $____________________________
(Registration, tutorials, banquet, extra proceedings)

[ ] Visa or MasterCard: Number________________________________________

 Expiration Date __________/___________
			 month / year

 Name as it appears on card: ______________________________________

[ ] Attached check payable to Association for Computational Linguistics
 or ACL


ACL						phone +1-908-873-3898
Priscilla Rasmussen				fax +1-908-873-0014
P.O. Box 6090
Somerset, NJ 08875, USA




 35th Annual Meeting of the Association for Computational Linguistics
		8th Conference of theEuropean Chapter of the
		 Association for Computational Linguistics
7-12 July 1997, Universidad Nacional de Educacion a Distancia, Madrid, Spain



 TELEPHONE:_____________________E-MAIL ADDRESS:________________________

 FAX NUMBER (for confirmation):________________________________________


 Single _____ _______________
 Double _____			_______________

 ARRIVAL DATE:________________________DEPARTURE DATE:__________________

 TOTAL NUMBER OF NIGHTS: _____________


 HOTELS IN ORDER OF PREFERENCE: 1)_____________________ ,
 2)__________________________ , 3)_____________________

 VISA __ Number: _____________________________
 MASTERCARD __ Expiration date: ____ / ____ / _____

 I authorize "Viajes el Corte Ingles" to charge ________ pesetas to my
 credit card.



"Single" means single/double occupied by one person.
"Double" means double occupied by two persons.
 All these fees include breakfast.
				Pesetas USD	 Pesetas USD
					as of 17 Apr 	 as of 17 Apr
 1: FLORIDA NORTE 	 9.000 $61.65 11.000	$75.35
 2: ESPAHOTEL PLZA. ESPA=D1A 10.000 $68.50 12.500	$85.63
 3: HOTEL GRAN VIA 	10.000 $68.50 12.500	$85.63


 35th Annual Meeting of the Association for Computational Linguistics
		8th Conference of theEuropean Chapter of the
		 Association for Computational Linguistics
7-12 July 1997, Universidad Nacional de Educacion a Distancia, Madrid, Spain

NAME _______________________________________________________________________
		Last			First			Middle

ADDRESS ____________________________________________________________________

AFFILIATION (for badge) ____________________________________________________

TELEPHONE __________________________________________________________________

E-MAIL ADDRESS _____________________________________________________________

APARTMENT REQUIREMENTS (prices are shown per night)

[ ] Single bedroom with individual bathroom 	$43
[ ] Single bedroom with shared bathroom 	$35

Roommate preference:________________________________________________________

Arrival Date:______________________ Departure Date:_________________________

Total number of nights:___________________________

Please send application with a check for the full amount by
May 30, 1997, to:

 Att: Soledad Pastor
 Fundacion Universidad Empresa 	
 c/ Serrano Jover, n5p7
 28015 Madrid, Spain
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue