LINGUIST List 13.139

Mon Jan 21 2002

Calls: Computational Ling, Computational Ling

Editor for this issue: Renee Galvis <>

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, ACL-02 Workshop CFP: Speech-to-Speech Translation: Algorithms and Systems
  2. Priscilla Rasmussen, ACL-02 Workshop CFP: Effective Tools and Methodologies for Teaching NLP and CL

Message 1: ACL-02 Workshop CFP: Speech-to-Speech Translation: Algorithms and Systems

Date: Fri, 18 Jan 2002 18:02:55 EST
From: Priscilla Rasmussen <>
Subject: ACL-02 Workshop CFP: Speech-to-Speech Translation: Algorithms and Systems

 ACL-02 Workshop on
 Speech-to-Speech Translation: Algorithms and Systems

 July 11 2002
 University of Pennsylvania, Philadelphia

 A workshop held as part of the
 Association for Computational Linguistics 40th anniversary meeting
 ACL-02 (
 Hosted by The Computer and Information Science Department and the
 Institute for Research in Cognitive Science
 University of Pennsylvania, Philadelphia
 July 7-12 2002



Facilitation of speech communication across language barriers is a
critical problem to solve for a global economy to thrive. Robust
systems for speech-to-speech translation (S2S) are clearly necessary
to move us towards achieving this goal. However, construction of such
systems is clearly extremely complex, involving research in Automatic
Speech Recognition(ASR), Text-to-Speech (TTS), Machine Translation
(MT), Natural Language Understanding (NLU) and Generation
(NLG). Although substantial progress in each of these components
individually has been made over the last two decades, simply
integrating individual ASR, NLU, MT, NLG, and TTS components to
produce S2S systems is not sufficient to produce acceptable results.
For example, conventional text-based MT systems have not been designed
to cope with the imperfect syntax and transcription errors which
characterize automatically transcribed conversational
speech. Traditional speech recognizers (ASR component) and speech
synthesizers (TTS component) have not been designed to recognize or
synthesize speakers' emotional expressions which convey meanings and
play an important role in the communications between human beings.
Therefore, speech-to-speech translation raises a whole new set of
algorithmic challenges over and above those associated with the
individual underlying technologies themselves.

We would like to bring together various researchers in the field
together to present the current state-of-the-art on speech-to-speech
translation and discuss the challenges involved in building a
functioning high performance system. We hope to hear about different
approaches to the S2S realization and exchange ideas about the
advantages and disadvantages of various approaches. The workshop will
specifically focus on natural language processing problems which are
unique and critical to producing robust speech-to-speech translation
systems and components.

We solicit submissions to the workshop in the following areas, however
any other topic related to the speech-to-speech translation is also

Machine Translation: 

- Algorithms for machine translation applicable to S2S
- Algorithms and systems for application specific and limited domain
machine translation
- Rule-based MT, statistical MT, template-based MT, interlingua-b ased
MT Speech recognition and TTS:
- Enhancing the performance of ASR in S2S using natural language
processing techniques
- TTS modules with highly naturalness and emotional expressions
- Robust speech recognition algorithms for S2S
- Challenges for extracting and conveying stress, prosody and emo
tions in speech across languages NLP:
- Natural language processing algorithms for S2S
- Natural language generation from meaning representations Language:
- Challenges for speech-to-speech translation across languages du e to
language characteristics, and suggestion of solutions
- Challenges for conveying stress, prosody and emotions in speech
across languages

System architecture and software integration

- Component architecture and design of modular S2S systems
- Portability of S2S systems to different languages and domains
- Implementation issues for robust and limited resource S2S

Multilingual Data Collection and System Evaluation:

- Evaluation metrics of spoken language translation quality
- Language resources and knowledge acquisition


We invite paper submissions from all researchers in the area of
 S2S translation, natural language processing, linguistics, and all 
related topics. All submissions will be reviewed by an international 
program committee. If sufficiently many high-quality papers are submitted, we 
will consider publishing selected papers in an edited volume.

Submissions should follow the two-column format of ACL proceedings
 and should not exceed eight (8) pages, including references. We recommend
 the use of ACL LaTeX style files or Microsoft Word Style files available

Deadline for paper submissions is March 15, 2002. Papers in pdf
format must be submitted electronically to:


The duration of the workshop is one full day. Only ACL-02 conference
participants are allowed to register for the workshop. The
registration fee is going to be set by the ACL-02 organizing
committee. The Proceedings of the Workshop will be published by the
ACL-02 organizing committee.


March 15, 2002: Deadline for workshop paper submissions
April 19, 2002: Notification of acceptance to authors
May 17, 2002: Deadline for camera-ready final version copies
July 11, 2002: S2S workshop in ACL-02 in Philadelphia


Yuqing Gao (IBM T. J. Watson Research Center)
Alex Waibel (Carneggie Mellon University)


Yuqing Gao, Project Lead, Speech-to-Speech Translation Research, IBM T.
 J. Watson Research Center
Alex Waibel, Professor & Director, Interactive Systems Lab, Carnegie 
 Mellon University (USA) & University Karlsruhe (Germany)
Hakan Erdogan, Speech-to-Speech Translation Research, IBM T. J. Watson
 Research Center
Michael Picheny, Manager, Speech Recognition Research, IBM T. J. Watson
 Research Center
Seiichi Yamamoto, Director, ATR Spoken Language Translation Research
 Laboratories (Japan)
Gianni Lazzari, Vice Director of ITC-irst (Italy)
Taiyi Huang, Professor, Institute of Automation, Chinese Academy of

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

Message 2: ACL-02 Workshop CFP: Effective Tools and Methodologies for Teaching NLP and CL

Date: Fri, 18 Jan 2002 18:27:50 EST
From: Priscilla Rasmussen <>
Subject: ACL-02 Workshop CFP: Effective Tools and Methodologies for Teaching NLP and CL


			 An ACL 2002 Workshop

	 July 7, 2002 (the day before the main conference)
			Philadelphia, PA, USA


		 Chris Brew, Ohio State University
		Dragomir Radev, University of Michigan


Natural Language Processing (and Computational Linguistics) courses
have been enjoying a large interest in the last few years. More and
more universities are offering both introductory and advanced
classes. Over the years, faculty from different departments have been
developing their classes by introducing and refining new lectures,
software, and projects. Some of the main challenges in teaching NLP

1. Teaching to a diverse audience, consisting of a mix of students in
 Linguistics, Computer Science, Information Science, and
 Bioinformatics; both undergraduate and graduate; and with a wide
 range of proficiency in linguistics, computer theory, or

2. Selecting an appropriate focus for a course, e.g., theory
 vs. applications, symbolic vs. empirical, text-only
 vs. text+speech, etc.

3. Finding an appropriate place of an NLP/CL course within a larger
 curriculum, e.g., in Artificial Intelligence, Computational
 Linguistics, Cognitive Science, or Language Engineering.

4. Finding the right links to related areas, such as Theoretical
 Linguistics, Information Retrieval, Speech Science, Cognitive
 Science, Artificial Intelligence, or Genetic/Molecular Biology.

5. Choosing appropriate assignments to provide the right mix of
 theoretical, programming and data analysis exercises.

6. Designing software for educational purposes and developing
 tutorials on existing software.

This ACL workshop on Effective Tools and Methodologies for Teaching
NLP/CL will address these challenges. The workshop will bring together
college faculty with experience in teaching such courses as well as
future teachers (e.g., current graduate students).


We will be soliciting short papers (4-6 pages) on the following

1. Effective course lectures

2. Innovative assignments and projects

3. Educational software

4. Web resources

5. Curriculum issues (e.g., developing an effective multi-course CL

6. Teaching NLP in different departments: Computer Science,
 Linguistics, Information Science, etc.

7. Connecting teaching and research

8. Seminar-style courses

9. Choice of programming languages (and programming requirements in

10. Teaching NLP in languages other than English

11. Evaluation issues (outcomes assessment, educational measurement,

In addition to these papers, the organizers will be collecting
pointers to educational resources on the Web, including course notes,
assignments, tutorials, software, and demos.

The workshop will feature a panel discussing longer-term activities
such as a mailing list for instructors, an archive of educational
materials, etc.

Submissions should be formatted according to the ACL style guide
( and must be in either
PS, PDF, or DOC format. These should be sent electronically to by the deadline shown below. Hard copies will be
accepted only if the authors explicitly make such arrangements the
co-chairs at least one week prior to the official submission date. In
that case, the hard copies will still have to arrive by the submission

We will assemble printed proceedings, however the ultimate goal of
this workshop would be laying the groundwork for further professional
collaboration in teaching NLP/CL, creating an ACL SIG, and building a
clearinghouse for educational materials.


Papers due: March 29, 2002
Acceptance or rejection notification: April 22, 2002
Camera-ready versions due: May 17, 2002
Workshop: July 07, 2002


Registration fees are $50 for regular participants and $0 (free) for
up to 10 lower income participants (e.g., graduate students and/or
participants from Eastern Europe, Africa, and other disadvantaged
areas of the world).

Candidates for registration fee waivers should indicate their interest
to the program co-chairs by April 22. Authors of accepted papers will
have priority, then authors of rejected papers, then all others.


Chris Brew (co-chair), Ohio State University,
Dragomir Radev (co-chair), University of Michigan,

Robert Dale, Macquarie University,
Graeme Hirst, University of Toronto,
Eduard Hovy, USC/ISI,
Andy Kehler, University of California, San Diego,
Lillian Lee, Cornell University,
Gina Levow, University of Chicago,
Diane Litman, University of Pittsburgh,
Chris Manning, Stanford University,
James Martin, University of Colorado,
Detmar Meurers, Ohio State University,
Massimo Poesio, University of Essex,
James Pustejovsky, Brandeis University,
Ehud Reiter, University of Aberdeen,
Philip Resnik, University of Maryland,
Ellen Riloff, University of Utah,
Matt Stone, Rutgers University,
Rich Thomason, University of Michigan,
Hans Uszkoreit, University of the Saarland and DFKI,
Bonnie Webber, University of Edinburgh,
Dekai Wu, Hong Kong University of Science and Technology,
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue