LINGUIST List 9.1646

Thu Nov 19 1998

Calls: Computational Ling., Computational Ling.

Editor for this issue: Karen Milligan <>

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


  1. Priscilla Rasmussen, Computational Linguistics/Tutorials
  2. Priscilla Rasmussen, Computational Linguistics/ General and Thematic Sessions

Message 1: Computational Linguistics/Tutorials

Date: Thu, 19 Nov 98 12:27:24 EST
From: Priscilla Rasmussen <>
Subject: Computational Linguistics/Tutorials

 Call for Tutorial Proposals

 Tutorials Chair:

 Richard Sproat
 Bell Labs - Lucent Technologies


 The ACL '99 Program Committee invites
 proposals for the Tutorial Program for
 ACL '99, to be held at the University of
 Maryland, College Park, MD, USA, June
 20--26, 1999. The tutorials for ACL '99
 will be held on June 20th.

 Each tutorial should be well-focused so
 that its core content can be covered in a
 three hour tutorial slot (including a 30
 minute break). In exceptional cases,
 6-hour tutorial slots are possible as

 There will be space and time for at most
 four three-hour tutorials.

 Submission Details

 Proposals for tutorials should contain:

 * A title and brief (< 500 word)
 content description of the tutorial
 * The names, postal addresses, phone
 numbers, and email addresses of the
 tutorial speakers, with
 one-paragraph statement of the
 speaker's(s') research interests and
 areas of expertise.
 * Any special requirements for
 technical needs (computer
 infrastructure, etc.)

 Proposals should be submitted by
 electronic mail, in plain ASCII
 (iso8859-1) text as soon as possible, but
 no later than December 18th, 1998.

 The subject line should be:


 Please submit your proposals and any
 inquiries to:

 Richard Sproat, ACL '99 Tutorials Chair
 Bell Laboratories, Lucent Technologies
 600 Mountain Avenue, Murray Hill, NJ
 07974 USA

 Practical Arrangements

 Accepted tutorial speakers must provide
 descriptions of their tutorials for
 inclusion in the Conference Registration
 material by March 1, 1999. The
 description must be provided in three
 formats: a latex version that fits onto
v 1/2 page; an ascii (iso8859-1) version
 that can be included with the email
 announcement; an HTML version that can be
 included on the Conference home page.

 Tutorial speakers will provide tutorial
 materials, at least containing copies of
 the overhead sheets used, by May 1, 1999.

 The current ACL policy is that tutorials
 are reimbursed at the following rate:
 $500 per session plus $25 per registrant
 in the range 21-50 plus $15 per
 registrant in excess of 50. Note that
 this is per tutorial, not per presenter:
 multiple presenters will split the
 proceeds, the default assumption being an
 even split. The ACL does not usually
 cover travel expenses except where the
 presenter(s) cannot get them through the
 usual mechanisms: for ACL members we
 assume that they would be coming to the
 meeting anyway. For people who are not
 ACL members, we would expect to pay for
 costs that they cannot get reimbursed

 Important Dates

 Submission Deadline for Tutorial
 18 Dec 1998
 Notification of acceptance of Tutorial
 28 Dec 1998
 Tutorial descriptions due to Tutorial
 1 Mar 1999
 Tutorial course material due to Tutorial
 1 May 1999
 Tutorials Date:
 20 June 1999
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: Computational Linguistics/ General and Thematic Sessions

Date: Thu, 19 Nov 98 12:31:25 EST
From: Priscilla Rasmussen <>
Subject: Computational Linguistics/ General and Thematic Sessions

		 ACL '99 Call for Papers
 37th Annual Meeting of the Association for Computational Linguistics
			 20--26 June, 1999
			University of Maryland

 [You may find it easier to read this information on the Web at]

1. Paper Sessions

1.1 Topics of Interest

In a break with tradition, at this year's ACL conference we are
experimenting with a new format. The technical sessions of the
conference will be of two kinds. There will be General Sessions of the
kind that have formed the conference programme in the past; however,
there will also be a number of special Thematic Sessions, somewhat
like a special issue of a journal, organised around themes proposed by
members of the computational linguistics community. Our aim is to
incorporate some of the intensity and excitement of the traditional
post-conference workshops, without replacing those workshops. The
conference structure will mean that the Thematic Sessions will run as
parallel sessions, resulting in smaller and more focussed
audiences. When you submit a paper to the conference, you will need to
consider whether you want to present the paper in the General Sessions
or in one of the Thematic Sessions, which are listed below. 

For the General Sessions, papers are invited on substantial, original,
and unpublished research on all aspects of computational linguistics,
including, but not limited to: pragmatics, discourse, semantics,
syntax and the lexicon; phonetics, phonology and morphology;
interpreting and generating spoken and written language; linguistic,
mathematical and psychological models of language; language-oriented
information retrieval and information extraction; corpus-based
language modeling; machine translation and translation aids; natural
language interfaces and dialogue systems; approaches to coordinating
the linguistic with other modalities in multi-media systems; message
and narrative understanding systems.

Papers submitted to the Thematic Sessions are more narrowly targeted
at specific topics. The complete list of Thematic Sessions is as
follows; further information about each can be found at the indicated URL. 

D1: Dialogue Management in Interactive Spoken Dialogue Systems
Chairs: Diane Litman and Marilyn Walker 
Motivation: The advent of real-time interactive spoken
	dialogue systems poses special challenges for dialogue
Topics: evaluation, dialogue strategies, repair, system integration, 
	learning/optimizing system behavior, corpus analysis, robust
	processing, and the requirements dialogue places on
	generation, speech recognition and synthesis. 

D2: Discourse Tagging: Uses, Results and Applications
Chairs: Marilyn Walker, Julia Hirschberg and Owen Rambow 
Motivation: Empirical approaches to discourse processing often rely on
	tagging texts or dialogues with discourse tags from a wide
	range of tag sets. 
Topics: Discourse tagging for training or testing models of discourse
	structure, reference, translation, speech acts, topic
	identification, and speech recognition. 

D3: Corpus-Based Approaches to Discourse and Dialogue
Chair: Nancy Ide 
This theme treats corpus-based work on any aspect of discourse and
	dialogue analysis, including co-reference, segmentation,
	discourse structure, parsing, generation, etc., especially in
	the light of relevance to practical applications. 

D4: Lexicon and Discourse: Connections through Structure and Semantics
Chairs: Laurence Danlos, Alistair Knott, and Bonnie Webber 
Motivation: With the lexicon becoming a central resource for computing
	properties of the sentence, one may consider similar gains for
	computing properties of discourse. 
Topics: Lexical semantics of discourse connectives and focus
	particles, discourse and lexical interpretation, lexicalized
	grammars for discourse. 

I1: NLP Techniques for Cross-Language Information Retrieval
Chair: Douglas Oard 
Motivation: Systems that use queries or examples in one natural
	language to find text or speech in another are becoming
	increasingly important. 
Topics: NLP techniques for query translation, cognate matching and
	interlingual matching techniques, cross-language gisting using
	summarization or gloss translation. 

I2: Exploring the Limits of Shallow Parsing
Chair: Gregory Grefenstette 
Shallow parsing techniques provide a partial analysis of the syntactic
	structures. Theme covers research into: quantifying
	identifiable linguistic phenomena in a corpus; evaluating
	accuracy of dependency relations extracted by shallow parsers;
	approximation of full parsing with shallow parsers. 

I3: Information Extraction from Spoken Language Data
Chairs: Lynette Hirschman and David Palmer 
Motivation: Identifying relevant syntactic and semantic items (such as
	names, dates, and events) in speech data requires robust
	processing of misspellings, transcription errors, tokenization
	ambiguities and disfluencies. 
Topics: algorithms, architectures, and evaluation techniques for noisy
	data information extraction 

I4: Natural Language Processing for Interactive Information Retrieval
Chair: Hinrich Sch|tze 
This theme solicits papers that use NLP to enable better interactive
	information retrieval. Examples include query analysis,
	disambiguation, and classification of queries into semantic
	hierarchies, but we are especially interested in novel ideas. 

I5: Robust Sentence-Level Interpretation
Chairs: Carolyn Penstein Rose and Alon Lavie 
In contrast to information extraction and shallow parsing techniques,
	in this session we focus on robust approaches to full sentence
	interpretation, with an emphasis on empirical evaluation. 
Topics: pre-parsing repair, robust parsing, post-parsing repair, and
	user interaction. 

I6: Topic Detection
Chairs: James Allan and Bruce Croft 
We examine discovering structure and themes across many texts: finding
	the topics that underlie the text. It includes summarization,
	theme extraction, TDT detection, concept extraction,
	high-quality clustering, and related evaluations. 

L1: Parsing of inflective, agglutinative and/or free word order languages
Chair: Jan Hajic 
	Parsing of languages displaying non-analytical, non-fixed word
	order behavior to a large extent poses specific problems which
	are expected to be addressed. All aspects of dealing with such
	problems are welcome, including morphological, syntactic and
	semantic processing. 

L2: MT/NLP for Languages of Low Diffusion
Chairs: Doug Jones and Boyan Onyshkevych 
Motivation: Adequate large-scale MT or other NLP systems do not exist
	for the bulk of the world's languages, nor are there
	significant on-line resources for them. 
Topics: how to build large-scale MT/NLP systems and resources for
	these other languages; how to leverage minimal resources
	(including native language expertise) 

L3: Word Segmentation and Lexical Acquisition in Asian Languages
Chair: Masaaki Nagata 
Motivation: Exchange ideas and experiences on word segmentation among 
	Asian researchers as well as between Asian and Western
Topics: Theories and applications of tokenization and dictionary 
	construction techniques for languages that do not put space
	between words, such as Chinese, Japanese, and Thai. 

M1: Automated Analysis and Evaluation of Free Text
Chairs: Jill Burstein and Claudia Leacock 
Motivation: To bring together researchers who are interested in the 
	evaluation of essays and other free text for purposes of
	assessment and instruction. 
Topics: Identification and analysis of textual features; generation of
	feedback to authors; evaluation of system results. 

M2: The Use of Large-Coverage Lexical Resources for Tagging and
Chair: Max Silberztein 
Motivation: To present dictionary-based projects and results whose
	starting point is either machine readable dictionaries, raw
	lists or large corpora 
Topics: large-coverage lexical resources, construction of
	dictionaries, corpus processing 

M3: Prosody Modelling In NLG/Speech Generation
Chairs: Elke Teich and Sandra Williams 
Motivation: Integrating natural language generation and speech
Topics: Reconciling syntactic, semantic and prosodic representations;
	determination of intonation focus and contour according to
	context; adaptations of NLG architectures for speech generation. 

M4: Design, Implementation, and Uses of Controlled Languages
Chairs: Tony Hartley and Cecile Paris 
Motivation: Controlled languages are increasingly used to enhance
	readability, facilitate automatic processing of documents, and
	guide input to generation systems. Important concerns are the
	development and enforcement of controlled languages. 
Topics: authoring environments, design principles, corpus analysis,
	controlled language applications. 

M5: Computational Psycholinguistics
Chair: Philip Resnik 
Motivation: Discussing empirical and theoretical studies on
	psychologically motivated computational models of human
	language processes, as opposed to NLP applications, emphasizing
	non-introspective data, statistical methods, and the relationship
	between linguistic competence and performance. 
Topics: Computational studies involving processes such as lexical
	access, parsing, interpretation, generation, disambiguation,

Before submitting a paper to a Thematic Session, you should read the
information about each of these themes provided on the separate web

During the conference itself, some sessions may be video-taped.
Presenters will be alerted to this possibility and will be able to
request that the cameras are turned off during their presentations.

1.2 Requirements

Requirements are the same regardless of whether your are submitting a
paper to the general sessions or the thematic sessions; see the
separate Call for Student Papers for information on requirements for
papers submitted to the Student Sessions. Papers should describe
original work; they should emphasize completed work rather than
intended work and they should indicate clearly the state of completion
of the reported results. Wherever appropriate, concrete evaluation
results should be included. A paper accepted for presentation at the
ACL Meeting cannot be presented or have been presented at any other
meeting with publicly available published proceedings. Papers that are
being submitted to other conferences must indicate this on the title

1.3 Format for Submission

The format of submissions is the same regardless of whether your are
submitting a paper to the General Sessions or the Thematic Sessions;
see the separate Call for Student Papers for information on
requirements for papers submitted to the Student Sessions. Authors
should submit preliminary versions of their papers for review, not to
exceed 3200 words (exclusive of references). Papers should be headed
by a title page containing the paper ID code (see below), the names of
all authors, the title, a short (5 line) summary, up to five keywords
specifying the subject area (for the General Sessions) or an
indication of the Thematic Session to which the paper is being
submitted, the word count (excluding figures and bibliography) and a
notice of multiple submission, if required. Papers outside the
specified length and/or without an ID code are liable to rejection
without review.

To identify each paper, an ID code must be acquired by filing an
electronic paper registration form, available on the web at on successful
completion of this form an ID code will be sent to the designated
author by e-mail. If you cannot access the electronic paper
registration form, send email to with subject
IDFORM for an automatic reply.

To assist in the refereeing process, we would be very grateful if
authors prepare a web-browsable (e.g. HTML, PostScript, PDF)
electronic version of their papers. The electronic paper registration
form contains a field where you can provide this information. 

We strongly recommend the use of ACL-standard LaTeX (plus bibstyle and
trivial example) or Word style files for the preparation of
submissions. These styles include a place for the required information
such as ID code and word count, and allow for a graceful transition to
the style required for publication. These files are available from
the conference web site at

If you cannot use the ACL-standard styles directly, a description of
the required format is at If you cannot
access this web page, send email to with subject
SUBSTYLE for an automatic reply.

1.4 Submission and Reviewing Procedure

The submission procedure is the same regardless of whether your are
submitting a paper to the General Sessions or the Thematic Sessions;
see the separate Call for Student Papers for information on submission
details for papers submitted to the Student Sessions. Four (4) paper
copies of each paper (printed on both sides of the page if possible)
should be submitted to the following address: 

	ACL Programme Committee
	c/o Ken Church
	AT&T Labs - Research 
	180 Park Ave, Office D235 
	PO Box 971 
	Florham Park
	NJ 07932-0971 

Enquiries can be addressed to the Programme Committee by email at (Robert Dale, Chair and Ken Church, co-Chair). In
extreme cases, if you cannot make contact electronically you can reach
us by sending a fax, clearly marked "ACL Programme Committee", to +61
2 9850 9529. This fax number is for information enquiries only. PLEASE

Reviewing of papers submitted to the General Sessions will, as in
previous years, be managed by an international Conference Programme
Committee consisting of Area Chairs, each of whom will have the
assistance of a team of reviewers. Reviewing of papers for the
Thematic Sessions will be managed by the chairs of the Thematic
Sessions, with the assistance of teams of reviewers; final decisions
on the technical programme content (both General Sessions and Thematic
Sessions) will be made by the Programme Committee. 

1.5 Schedule

Submissions must be received by January 25th 1999. Late submissions
(those arriving on or after January 26th 1999) will be returned
unopened. Acknowledgements will be emailed soon after
receipt. Notification of acceptance will be sent to authors (by email)
on March 22nd 1999. Camera-ready copies of final papers prepared in a
double-column format, preferably using a laser printer, must be
received by May 3rd 1999, along with a signed copyright release
statement. Detailed formatting guidelines will be provided to authors
with their acceptance notice. The paper sessions, including general,
theme and student papers, will take place on June 23rd--26th 1999.

2. Student Sessions

There will again be special Student Sessions organized by a committee
of ACL graduate student members. ACL student members are invited to
submit short papers on any of the topics listed above for the General
Sessions. The papers will be reviewed by a committee of students and
faculty members for presentation in workshop-style sessions and
publication in a special section of the conference proceedings. A
separate Call for Papers for the Student Sessions is being issued and
is available at 

3. Tutorials

The meeting will include a programme of tutorials on June 20th 1999
immediately preceding the workshops and technical sessions, and at the
same venue as the conference. A separate Call for Tutorial Proposals
is being issued and is available at 

4. Workshops

As in other years, ACL '99 will be accompanied by a number of
workshops. These will be held on June 21st--22nd 1999, immediately
after the tutorials and before the technical sessions. The ACL has a
policy on workshops. A separate Call for Workshop Proposals will be
issued soon. 

5. Demos

A separate Call for Demo Proposals will be issued at a later date. 

6. Venue and Local Organisation

The conference will be held at the University of Maryland from 20th
through 26th June, 1999. The Local Arrangements Committee is chaired
by Bonnie Dorr; see for local
arrangements information. 

7. Timetable

The dates here pertain only to the General Sessions and Thematic
Sessions: see the separate Calls for Student Session Papers, Tutorial
Proposals and Workshops for the timetabling associated with those
elements of the conference. 

Paper submissions deadline: January 25, 1999 
Notification of acceptance: March 22, 1999 
Camera ready papers due: May 3, 1999 
ACL'99 Conference: June 20--26, 1999 
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue