Copy Link
Add to Bookmark
Report
NL-KR Digest Volume 09 No. 30
NL-KR Digest (Thu Jun 11 11:22:10 1992) Volume 9 No. 30
Today's Topics:
Query: References for "Speech Tagging"
Query: email addresses (related to stochastic NLP and SR)
Query: Learning From Using Expert Systems
Announcement: Demonstrations and Exhibits at ACL-92
Announcement: Survey of Computational Linguistics Courses
Announcement: Connectionism & Reasoning - BBS Call for Commentators
CFP: 6th European ACL Conference
Submissions: nl-kr@cs.rpi.edu
Requests, policy: nl-kr-request@cs.rpi.edu
Back issues are available from host archive.cssage.rpi.edu [128.113.53.18] in
the files nl-kr/Vxx/Nyy (ie nl-kr/V01/N01 for V1#1), mail requests will
not be promptly satisfied. Starting with V9, there is a subject index
in the file INDEX. If you can't reach `cs.rpi.edu' you may want
to use `turing.cs.rpi.edu' instead.
BITNET subscribers: we now have a LISTSERVer for nl-kr.
You may send submissions to NL-KR@RPIECS
and any listserv-style administrative requests to LISTSERV@RPIECS.
-----------------------------------------------------------------
To: nl-kr@cs.rpi.edu
Date: Tue, 2 Jun 92 11:04:44 -0600
From: miller%jensen.cs@hellgate.utah.edu (Cliff Miller)
Subject: Query: References for "Speech Tagging"
I'm doing a literature search on "speech tagging", where you have 2 inputs --
digitized speech and corresponding text -- and the problem is to find the
where the words in the text occur in the digitized data. It is thus "tagging"
the digitized data with phonemic and word/sentence boundary information in
the case where you already have both types of information but don't know
what corresponds to what.
Has there been work done on this? Please send references to any related work
directly to:
miller@cs.utah.edu
I have a background in linguistics and computer science, but I'm new to the
speech recognition field. Any good introductory references to the field
will also be appreciated.
Thank you.
Cliff Miller
------------------------------
To: nl-kr@cs.rpi.edu
Newsgroups: comp.ai.nlang-know-rep,comp.ai
From: ueberla@cs.sfu.ca (Joerg Ueberla)
Subject: Query: email addresses (related to stochastic NLP and SR)
Keywords: Natural Language Processing, Speech Recognition
Date: Mon, 8 Jun 1992 22:01:14 GMT
Hi,
I am looking for the following email addresses
1)Julian Kupiec, Xerox Palo Alto Research Center
2)someone at IBM T.J. Watson Research Center, more specifically
Jelinek,F., Mercer,R.L., or Lafferty,J.D.
3)someone at the University of Leeds, more specifically
Atwell,E.S., O'Donoghue,T. ,Souter,C.
4)J.H.Wright, University of Bristol, U.K.
If you have any of the above, or if you could help me in getting it, I
would really appreciate your help.
thanks in advance,
Joerg
ueberla@cs.sfu.ca
------------------------------
To: nl-kr@cs.rpi.edu
Date: Tue, 9 Jun 1992 20:40 MDT
From: FORDJ@byu.edu
Subject: Query: Learning From Using Expert Systems
Newsgroups: comp.ai.nlang-know-rep,comp.ai,comp.ai.edu,comp.ai.philosophy
I am investigating the so-called "learning from use" effect that
occurs when users interact with expert systems or other types of
job aids. I have accumulated a set of references on this topic,
including several dissertations, but I am making one last effort
to find information before my prospectus is finalized.
I would be grateful for any pointers to research studies,
textbooks, tech reports, personal anecdotes or whatever concerning
how users learn, do not learn, misconstrue, etc. the knowledge
contained in an expert system as a result of using it to solve
problems. I am also interested in information about the effects
on learning and otherwise when users are overly impressed by an
expert system because it is "artificial intelligence." In short,
do users learn from using expert systems? What factors influence
this?
As always, criticisms, comments and well-articulated flames are
solicited and appreciated. I will post a summary of this and
possibly (haven't decided about this yet) send a copy of my
prospectus to interested parties.
Thanks,
John M. Ford BYU Instructional Psychology Program
740 South 50 East (801) 224-9039
Orem, UT 84058 fordj@yvax.byu.edu
------------------------------
To: nl-kr@cs.rpi.edu
Date: Sun, 7 Jun 92 17:10:37 -0400
From: walker@flash.bellcore.com (Don Walker)
Subject: Announcement: Demonstrations and Exhibits at ACL-92
We are encouraging exhibits and demonstrations at ACL-92, the 30th
Annual Meeting of the Association for Computational Linguistics,
which will be held from 28 June through 2 July in Newark, Delaware,
in the United States.
Authors of papers or academics without grants or contract support may
present their demonstrations without making a donation, but universities
and research labs that demo research rather than commercial software,
and small entrepreneurs, are requested to donate $125 to cover expenses.
Commercial software and hardware enterprises are requested to donate $350.
If you are interested or can suggest names to contact, please send
email addresses and/or phone numbers to:
Daniel Chester
University of Delaware
Computer and Information Sciences
Newark, DE 19716, USA
chester@dewey.udel.edu
+1-302 831-1955
------------------------------
To: nl-kr@cs.rpi.edu
Date: Tue, 9 Jun 92 14:42:30 -0400
From: bonnie@umiacs.UMD.EDU (Bonnie Dorr)
Subject: Announcement: Survey of Computational Linguistics Courses
SURVEY OF COMPUTATIONAL LINGUISTICS COURSES
URGENT NEED FOR INFORMATION
As a follow-on to the Directory of Computational Linguistics Courses
recently compiled by Martha Evens, the Association for Computational
Linguistics will publish a new edition of the Survey of Computational
Linguistics Courses. (See Computational Linguistics, volume 12 (1986)
for the previous version compiled by Robin Cohen.) We are eager to
include two types of courses: those that teach computational
linguistics as the sole topic and those that teach computational
linguistics as one of many topics. The survey will allow us to share
with colleagues ideas on how to teach computational linguistics. It
will also provide an idea of how the field of computational
linguistics is being portrayed to potential new researchers.
Our listing will include the name and address of the University and
Department(s) offering the course, the name and number of the course,
the type of course, and information about the syllabus (e.g., topics,
texts used, format, workload, enrollment, duration, and assistance).
In addition we will include some statistics on the responses (i.e.,
total number of courses having particular characteristics) and a
bibliography of the most of frequently cited references.
Please request guidelines as to content and format and send
information to:
Ms. Sandy Tsue
UMIACS
A.V. Williams Building
University of Maryland E-mail: cl-survey@umiacs.umd.edu
College Park, MD 20742 Tel: (+1-301)405-6722
Re: CL-SURVEY Fax: (+1-301)314-9658
Note: e-mail is preferred.
If your institution was listed in the 1986 compilation, you may
request a copy of your previous entry.
Thank you for your participation in this endeavor.
Professor Bonnie Dorr
Department of Computer Science and UMIACS
University of Maryland
------------------------------
To: nl-kr@cs.rpi.edu
Newsgroups: comp.ai,comp.ai.nlang-know-rep,comp.ai.neural-nets
From: harnad@phoenix.princeton.edu (Stevan Harnad)
Subject: Announcement: Connectionism & Reasoning - BBS Call for Commentators
Keywords: dynamic bindings, memory, neural oscillations, synchrony
Date: Wed, 10 Jun 1992 01:51:31 GMT
Below is the abstract of a forthcoming target article on connectionism
and reasoning by Shastri & Ajjanagadde. It has been accepted for
publication in Behavioral and Brain Sciences (BBS), an international,
interdisciplinary journal that provides Open Peer Commentary on
important and controversial current research in the biobehavioral and
cognitive sciences. Commentators must be current BBS Associates or
nominated by a current BBS Associate. To be considered as a commentator
on this article, to suggest other appropriate commentators, or for
information about how to become a BBS Associate, please send email to:
harnad@clarity.princeton.edu or harnad@pucc.bitnet or write to:
BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771]
To help us put together a balanced list of commentators, please give some
indication of the aspects of the topic on which you would bring your
areas of expertise to bear if you were selected as a commentator. An
electronic draft of the full text is available for inspection by anonymous
ftp according to the instructions that follow after the abstract.
____________________________________________________________________
FROM SIMPLE ASSOCIATIONS TO SYSTEMATIC REASONING:
A Connectionist representation of rules, variables, and dynamic
bindings using temporal synchrony
Lokendra Shastri
Computer and Information Science Department
University of Pennsylvania
Philadelphia, PA 19104
shastri@central.cis.upenn.edu
Venkat Ajjanagadde
Wilhelm-Schickard-Institut
University of Teubingen
Sand 14 W-7400 Tuebingen, Germany
nnsaj01@mailserv.zdv.uni-tuebingen.de
KEYWORDS: knowledge representation; reasoning; connectionism;
dynamic bindings; temporal synchrony, neural oscillations, short-
term memory; long-term memory; working memory; systematicity.
ABSTRACT: Human agents draw a variety of inferences effortlessly,
spontaneously, and with remarkable efficiency --- as though these
inferences were a reflex response of their cognitive apparatus.
Furthermore, these inferences are drawn with reference to a large body
of background knowledge. This remarkable human ability is hard to
explain given findings on the complexity of reasoning reported by
researchers in artificial intelligence. It also poses a challenge for
cognitive science and computational neuroscience: How can a system of
simple and slow neuron-like elements represent a large body of
systematic knowledge and perform a range of inferences with such speed?
We describe a computational model that takes a step toward addressing
the cognitive science challenge and resolving the artificial
intelligence puzzle. We show how a connectionist network can encode
millions of facts and rules involving n-ary predicates and variables
and can perform a class of inferences in a few hundred milliseconds.
Efficient reasoning requires the rapid representation and propagation
of dynamic bindings. Our model achieves this by representing (1)
dynamic bindings as the synchronous firing of appropriate nodes, (2)
rules as interconnection patterns that direct the propagation of
rhythmic activity, and (3) long-term facts as temporal pattern-matching
sub-networks. The model is consistent with recent neurophysiological
findings which suggest that synchronous activity occurs in the brain
and may play a representational role in neural information processing.
The model also makes specific, psychologically significant predictions
about the nature of reflexive reasoning. It identifies constraints on
the form of rules that may participate in such reasoning and relates
the capacity of the working memory underlying reflexive reasoning to
biological parameters such as the frequency at which nodes can sustain
oscillations and the coarseness of synchronization.
- -------------------------------------------------------------
To help you decide whether you would be an appropriate commentator for
this article, an electronic draft is retrievable by anonymous ftp from
princeton.edu according to the instructions below (the filename is
bbs.shastri). Please do not prepare a commentary on this draft. Just
let us know, after having inspected it, what relevant expertise you
feel you would bring to bear on what aspect of the article.
- ------------------------------------------------------------
To retrieve a file by ftp from a Unix/Internet site, type either:
ftp princeton.edu
or
ftp 128.112.128.1
When you are asked for your login, type:
anonymous
Enter password as per instructions (make sure to include the specified @),
and then change directories with:
cd pub/harnad
To show the available files, type:
ls
Next, retrieve the file you want with (for example):
get bbs.shastri
When you have the file(s) you want, type:
quit
Certain non-Unix/Internet sites have a facility you can use that is
equivalent to the above. Sometimes the procedure for connecting to
princeton.edu will be a two step process such as:
ftp
followed at the prompt by:
open princeton.edu
or
open 128.112.128.1
In case of doubt or difficulty, consult your system manager.
- ---------
JANET users who do not have the facilty for interactive file
transfer mentioned above have two options for getting BBS files. The
first, which is simpler but may be subject to traffic delays, uses
the file transfer utility at JANET node UK.AC.FT-RELAY. Use standard
file transfer, setting the site to be UK.AC.FT-RELAY, the userid as
anonymous@edu.princeton, for the password your-own-userid@your-site
[the "@" is crucial], and for the remote filename the filename
according to Unix conventions (i.e. something like
pub/harnad/bbs.authorname). Lower case should be used where
indicated, with quotes if necessary to avoid automatic translation
into upper case. Setting the remote filename to be (D)pub/harnad
instead of the one indicated above will provide you with a directory
listing.
The alternative, faster but more complicated procedure is to log on
to JANET site UK.AC.NSF.SUN (with userid and password both given as
guestftp), and then transfer the file interactively to a directory
on that site (named by you when you log on). The method for transfer
is as described above under 'Certain non-Unix/Internet sites', or
you can make use of the on-line help that is available. Transfer of
the file received to your own site is best done from your own site;
the remote file (on the UK.AC.NSF.SUN machine) should be named as
directory-name/filename (the directory name to use being that
provided by you when you logged on to UK.AC.NSF.SUN). To be sociable
(since NSF.SUN is short of disc space), once you have received the
file on your own machine you should go back to UK.AC.NSF.SUN and
delete it from your directory there.
[Thanks to Brian Josephson for the above detailed UK/JANET
instructions; similar special instructions for file retrieval
from other networks or countries would be appreciated and will
be included in updates of these instructions.]
- --
Where the above procedures are not available (e.g. from Bitnet or other
networks), there are two fileservers -- ftpmail@decwrl.dec.com and
bitftp@pucc.bitnet -- that will do the transfer for you. Send either one the
one line message:
help
for instructions (which will be similar to the above, but will be in
the form of a series of lines in an email message that ftpmail or
bitftp will then execute for you).
- ------------------------------------------------------------
- -
Stevan Harnad Department of Psychology Princeton University
harnad@clarity.princeton.edu / harnad@pucc.bitnet / srh@flash.bellcore.com
harnad@learning.siemens.com / harnad@elbereth.rutgers.edu / (609)-921-7771
------------------------------
To: nl-kr@cs.rpi.edu
Date: Tue, 9 Jun 92 16:57:47 +0200
From: Louis des Tombe <destombe@let.ruu.nl>
Subject: CFP: 6th European ACL Conference
FIRST NOTIFICATION AND CALL FOR PAPERS
Sixth Conference of the European Chapter
of the Association for Computational Linguistics
21-23 April 1993
Onderzoeksinstituut voor Taal en Spraak (OTS)
Research Institute for Language and Speech
University of Utrecht, The Netherlands
Purpose: This conference is the sixth in a series of biennial
conferences on computational linguistics sponsored by the European
Chapter of the Association for Computational Linguistics. Previous
conferences were held in Pisa (September 1983), Geneva (March 1985),
Copenhagen (April 1987), Manchester (April 1989) and Berlin (April
1991). Although hosted by a regional chapter, these conferences are
global in scope and participation. The European Chapter represents a
major subset of the ACL. The conference is open to both members and
nonmembers of the Association.
Scope: Papers are invited on all aspects of computational linguistics,
including, but not limited to: morphology, syntax, semantics,
discourse analysis, pragmatics, grammar formalisms, formal languages,
software tools, knowledge representation, AI-methods in computational
linguistics, analysis and generation of language, computational
lexicography and lexicology, lexical databases, machine translation,
computational aids to translation, speech analysis and synthesis,
natural language interfaces, dialogue, computer-assisted language
learning, corpus analysis and corpus-based language modelling, and
information retrieval and message understanding.
Special Sessions/Tutorials: The Programme Committee plans special
sessions around the following themes:
- logic and computational linguistics
- data-oriented methods in computational linguistics
This thematic orientation will be further developed in a tutorial
programme to be held the day preceding the conference (20 April 1993).
Details will be provided in the circular of October 1992.
Submission: Authors should submit an extended abstract of their
papers, or in case of hardcopy 6 copies, to the Programme Committee at
the following address:
EACL-93 Programme Committee
OTS
Trans 10
NL-3512 JK Utrecht
The Netherlands
Phone: (+31) 30-392531
Fax: (+31) 30-333380
Email: eacl93@let.ruu.nl
The first page should include the title, the name(s) of the author(s),
complete addresses (including e-mail), a specification of the topic
area (one or two keywords, preferably from the list above), and an
indication of whether the paper addresses one of the themes of the
Special Sessions. The extended abstract should not exceed 5 pages A4.
It should contain sufficient information to allow the referees and the
Programme Committee to determine the scope of the work and its
relation to relevant literature. Contributions should report on
original research that has not been presented elsewhere. Electronic
submission is preferred, using standard LaTeX or plain ASCII. In case
of problems with this, contact the organizers at the above address.
For future final versions, hardcopy or LaTeX files will be accepted.
Schedule: The deadline for submission is 1 December 1992. Authors
will be notified of acceptance by 1 February 1993. Camera-ready
copies of the final papers must be postmarked before 5 March 1993, and
received by 12 March 1993, along with a signed copyright release
statement. Papers not received by the due date will not be included
in the conference proceedings, which will be published in time for
distribution to everyone attending the conference.
Programme Committee: The Programme Committee will be co-chaired
by Louis des Tombe, Steven Krauwer and Michael Moortgat (OTS, Utrecht).
Local Arrangements: Contact Nadine Buenen or Joke Dorrepaal at the above
address. More information on local arrangements will be provided in the
next circular.
Other Activities: A programme of demonstrations and exhibits is
planned. For information, contact the EACL address above.
------------------------------
End of NL-KR Digest
*******************
