Copy Link
Add to Bookmark
Report
NL-KR Digest Volume 10 No. 11
NL-KR Digest (Tue Mar 9 14:06:42 1993) Volume 10 No. 11
Today's Topics:
Query: Parts of speech routines
Talk: Itsuki Noda on Semantics Nets and NNs at BBN
CFP: EDBT 94 - Extending Database Technologies
Announcement: Proceedings of Conf. Cognition & Representation
Submissions: nl-kr@cs.rpi.edu
Requests, policy: nl-kr-request@cs.rpi.edu
Back issues are available from host archive.cs.rpi.edu [128.213.3.18] 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@RPITSVM
and any listserv-style administrative requests to LISTSERV@RPITSVM.
[ The article backlog is now purged and NLKR is back up to date. Hope
you all survived the three week deluge of Digests. I am now pursuing
the huge adminstrative backlog, and the search for a new moderator has
turned up some very promising results for the future of this Digest. -CW ]
-----------------------------------------------------------------
To: nl-kr@cs.rpi.edu
From: 72657.2203@compuserve.com
Date: Tue, 9 Mar 93 09:40:42 EST
Subject: Query: Parts of speech routines
I am developing a natural language processing system using neural networks
and need some routines (preferably in C), which will classify words by
parts of speech. If anyone knows where I can find some, please respond
to 72657.2203@COMPUSERVE.COM
Thanks,
Greg
------------------------------
To: nl-kr@cs.rpi.edu
Date: Wed, 10 Mar 93 10:41:34 EST
From: Helene George <hgeorge@BBN.COM>
Subject: Talk: Itsuki Noda on Semantics Nets and NNs at BBN
AI Seminar Series
Speaker: Itsuki Noda
Electrotechnical Laboratory, Toyko
Where: 70 Fawcett St., 15-300
When: March 17, 1993
Time: 2:30 - 3:30
ABSTRACTS:
"Formalization of Semantic Networks for Neural Networks",
In this paper, a formalization of semantic networks which is suitable
for representing by patterns on neural networks is proposed. In order
to represent semantic networks on neural networks, we focus on the
function of semantic networks to track concepts along links between
concepts, and incorporate a topology into concept sets in order to
represent rules. Furthermore, I present a method how to determine
semantic networks by external behavior. Moreover, I show an example
of implementation this formalization into neural networks.
- ---------------------------------------------------------------------
"Natural Language Processing System that consists of Cooperative Modules",
In this presentation, we describe a plan of a system for natural
language processing that is based on "cooperative" principle. This
system consists of several modules of lexicon, syntax, semantics and
so on and each module runs parallel without control from each other.
These modules try to have a hypothesis in the field where they work,
and in order to do this they exchange information to confirm or change
hypotheses of each module. But if necessary, each module can work
alone although in low quality. So even if some module can not perform
its work, other modules can output some hypothesis without deadlock.
This means that the system can analyze semantics of sentence that is
illegal in syntax.
The main aim of this project is to show how useful the programming
based on cooperative principle is. If this programing style is good,
we will be able to build complex systems like natural language
processing and add a new module to the system without wholly changing
the system.
------------------------------
To: nl-kr@cs.rpi.edu
Date: Wed, 10 Mar 1993 11:34:56 +0100 (MET)
From: Matthias Jarke <jarke@picasso.informatik.rwth-aachen.de>
Subject: CFP: EDBT 94 - Extending Database Technologies
=========================
EDBT 94 CALL FOR PAPERS
=========================
The Fourth International Conference on
EXTENDING DATABASE TECHNOLOGY
promoted by
The EDBT Foundation
sponsored by
British Computer Society
ESPRIT Network of Excellence IDOMENEUS
28 - 31 March 1994
St John's College, Cambridge, UK
Conference Themes
=================
With successful conferences in Venice (1988 and 1990) and in Vienna
(1992), EDBT has established itself as Europe's premier international
conference on databases.
EDBT 94 in Cambridge will provide a forum for the latest results in the
research, development and use of database technology, and will encourage
active interchange between all those involved in this field.
The UK has a strong database research community, leading international
technology suppliers, and it has many large commercial users of database
systems. Their presence will ensure a high level of debate.
Major topics for the conference will include, but are not limited to:
- Client-Server and open networked database systems
- Distributed database techniques
- Advanced transaction processing techniques
- Object-Oriented, Deductive, and Active databases
- Multimedia and hypermedia database systems
- Advanced user interfaces for data manipulation
- Databases and programming systems
- Information resource dictionaries/repositories
- Highly parallel database systems
- Advanced database applications
- Database implementation (query optimisation, integrity and security)
In addition to the presented papers, the conference will include panel
discussions, industrial sessions, and high quality tutorials by
internationally recognised speakers. There will be an accompanying
exhibition.
Information for Authors
=======================
Five copies in English of an original, unpublished paper, limited to
5000 words, should be submitted before the 18th June 1993 to:
Matthias Jarke
RWTH-Aachen
Informatik V
Ahornstrasse 55
5100 Aachen
Germany
E-mail: edbt94@picasso.informatik.rwth-aachen.de
Submitted papers must not be under consideration for publication
elsewhere during the review process. The Conference Proceedings will be
edited and published by Springer-Verlag (in the Lecture Notes in
Computer Science series) and will be distributed at the conference.
Conference Organisation
=======================
Conference Chairman
- ------------------
J Bubenko (SISU, Sweden)
Programme Committee
- ------------------
M Jarke (RWTH Aachen) - Chairman
S Abiteboul (France) G Moerkotte (Germany)
M Agosti (Italy) J Mylopoulos (Canada)
R Bayer (Germany) S Nishio (Japan)
E Bertino (Italy) A Olive (Spain)
J Bocca (Chile/UK) M E Orlowska (Australia)
A Borgida (USA) M Papazoglou (Australia)
M Brodie (USA) A Pirotte (Belgium)
M Carey (USA) A Reuter (Germany)
J Clifford (USA) R v.d Riet (Netherlands)
P Dadam (Germany) T Risch (Sweden)
M Freeston (Germany) C Rolland (France)
H P Frei (Switzerland) T Rose (Canada)
H Garcia-Molina (USA) H Schek (Switzerland)
G Gottlob (Austria) T Sellis (Greece)
P Gray (UK) D Shasha (USA)
V Jagadish (USA) E Simon (France)
K G Jeffery (UK) A Solvberg (Norway)
L Kalininchenko (Russia) A Stogny (Ukraine)
H Kangassalo (Finland) M Stonebraker (USA)
M Lenzerini (Italy) K Subieta (Poland)
F Lochovsky (Hong Kong) B Thalheim (Germany)
P Loucopoulos (UK) Y Vassiliou (Greece)
L Mark (Denmark/USA) J Widom (USA)
F Matthes (USA) J Zlatuska (Czechoslovakia)
Organising Committee
- -------------------
K G Jeffery (SERC Rutherford Appleton Laboratory) - Chairman
A Duckworth (BCS) J Kennedy (Napier)
W A Gray (Cardiff) K Moody (Cambridge)
M S Jackson (Wolverhampton) B J Read (SERC)
R G Johnson (Birkbeck) G Sharman (IBM)
Regional Co-ordinators
- --------------
R Andersen (Norway) A Pirotte (Belgium)
R Carapuca (Portugal) F Plasil (Czechoslovakia)
J Fong (Hong Kong) S Sa (China)
J B Grimson (Ireland) F Saltor (Spain)
M Kersten (Netherlands) G Schlageter (Germany)
K-C Lee (Taiwan) D Shasha (USA)
M Leonard (Switzerland) C K Tan (Singapore)
B G Lundberg (Sweden) C Thanos (Italy)
S Nishio (Japan) L Tucherman (Brazil)
M E Orlowska (Australia) Y Vassiliou (Greece)
EDBT Foundation Consultants
- --------------------------
S Ceri (Milan) J Schmidt (Hamburg)
M Missikoff (Rome)
*******************************************************************
* *
* IMPORTANT DATES *
* *
* 18 June 1993 - submission deadline *
* 20 September 1993 - acceptance notification *
* 1 November 1993 - camera-ready copy due *
* *
*******************************************************************
Further Information
===================
The Chairman of the Organising Committee is
Dr Keith G Jeffery
SERC Rutherford Appleton Laboratory
E-mail: kgj@ib.rl.ac.uk
For details of the conference or exhibition, please contact the
secretariat:
Miss Anna Duckworth
EDBT 94 Conference
British Computer Society
PO Box 1454
Station Road
SWINDON SN1 1TG, UK
Telephone (+44) 793 480269
Facsimile (+44) 793 480270
To ensure that you receive the Advance Programme and that you are able
to take advantage of early registration, please send your name and
address to the secretariat. (You may alternatively notify the
Organising Committee Chairman by e-mail if you wish.) Cambridge is a
popular tourist city so accommodation should be reserved in advance.
Organisations interested in taking part in the exhibition or an
industrial session, or in possible sponsorship of the conference or
social events are also invited to contact the organisers.
Conference Location
===================
Cambridge is Britain's leading scientific university. It has a rich
history of innovation in many fields, including some of the earliest
work on the stored program computer, and is a centre for modern high
technology industry. The city is set in beautiful countryside, and
contains some of Europe's finest university architecture in a unique
riverside setting facing "The Backs".
The conference and residential accommodation will be in St John's
College, which dates from the 16th century. The college is situated on
both banks of the River Cam, connected by the famous "Bridge of Sighs"
which we have featured in our conference logo, and is well equipped with
all facilities. Main sessions will be in the modern Fisher Building.
Cambridge is less than one hour from London by road or rail, and it has
excellent links with continental Europe. Sea travellers may reach
Cambridge from the ferry ports at Felixstowe (66 miles), Harwich (87
miles) or Dover (122 miles). Nearby international airports are Stansted
(24 miles), Heathrow (83 miles) or Gatwick (93 miles), all with good
coach, rail and motorway connections. The opening of the Calais-Dover
tunnel adds another direct travel option for visitors from the
continent.
========================================================================
- --------------------------------------------------------------
------------------------------
To: nl-kr@cs.rpi.edu
Newsgroups: comp.ai,comp.ai.philosophy,comp.ai.nlang-know-rep,...
From: rapaport@cs.buffalo.edu (William J. Rapaport)
Subject: Announcement: Proceedings of Conf. Cognition & Representation
Nntp-Posting-Host: adara.cs.buffalo.edu
Date: Wed, 24 Feb 1993 18:28:57 GMT
Announcing...
PROCEEDINGS OF THE CONFERENCE ON COGNITION AND REPRESENTATION
Held at the SUNY Buffalo Center for Cognitive Science, April 1992, the
proceedings of this conference are now available as a technical report.
The price is US$10.00. Payment may be made by check made payable to
"Center for Cognitive Science", and orders should be sent to:
Ms. Dawn Phillips
Center for Cognitive Science
652 Baldy Hall
SUNY Buffalo
Buffalo, NY 14260
USA
Email inquiries should be sent to dcp@cs.buffalo.edu.
Phone inquiries should be made to 716-645-3794.
=========================================================================
The contents of the Proceedings are as follows (abstracts of the papers
are appended to this email):
TIM VAN GELDER
"Distributed Represenation--An Outline"
DAVID BANACH
"Representing, Similarity, and the Storage of Information"
ANN ROBYNS
"Primary and Mature Conceptual Structures--Evidence from Child Language"
JOHN KOUNIOS and PHILLIPS HOLCOMB
"Inferring Semantic-Memory Structure from Behavioral and Electrophysiological
Measures"
VINOD GOEL
"Specifying Classifying Representational Systems: A Critique and Proposal for
Cognitive Science"
STEVEN HORST
"Notions of Representation and the Diverging Interests of Philosophy and
Empirical Science"
JOHN F. SOWA:
"Logic Foundations for Representing Object-Oriented Systems"
BARBARA L. SPEICHER
"Disentangling Conceptual and Linguistic Knowledge"
BARBARA ABBOTT and LARRY HAUSER
"Natural Language and Thought"
MICHAEL TARR
"Behavioral and Computational Constraints in Human Shape Representation"
WHITMAN RICHARDS
"Is Perception for Real?"
K. N. LEIBOVIC
"Brain Mechanisms for Perceptual Representation"
ABSTRACTS
TIM VAN GELDER
"Distributed Represenation--An Outline"
What is distributed representation? This question is central to
many practical and philosophical concerns, both in connectionism and in
cognitive science more generally, yet it has never been given an answer
that is both comprehensive and precise. In this talk I propose a way
of defining distribution that, on one hand, reveals the fundamental
similarity between (for example) the gross functional neuroanatomy of
the various brain areas and connectionist hidden unit activity patterns,
while on the other is strict enough to yield mathematically precise
descriptions in real modeling contexts. The key concept is that of
semantic superimposition; I elaborate this suprisingly tricky concept,
offer a formal framework rendering it precise, and explain how
superimposition can be incorporated into a general definition of
distributed representation.
DAVID BANACH
"Representing, Similarity, and the Storage of Information"
Representing is an activity, a process through which a subject cognizes
the world. Most theories of representation take one element or
component of this activity and identify it as the representation by
attributing to the element, in isolation, properties it has only in the
context of the act of representing. In particular, I argue that the
similarity of an icon to an object is neither necessary nor sufficient
for representation and that seeing why this is so reveals fundamental
defects with views that see representations as (1) stored information,
which represents in virtue of an isomorphism effected by an information
storage and retrieval algorithm; or (2) as a distributed pattern of
activity over a set of units or phase space, which represents in virtue
of a topological isomorphism to the represented object. All of these
models identify the representation with some element of the cognitive
process that cannot intrinsically represent apart from its situation in
a wider context. I argue that such models of representation will fail
to account for the cognitive role of representation as long as they
mistake part of the representing process for the representating itself.
ANN ROBYNS
"Primary and Mature Conceptual Structures--Evidence from Child Language"
Currently, in semanic enquiry some researchers represent
lexical-conceptual structure as an architecture of sets and truth
conditions. Others borrow from psychology such terms as 'conceptual
primitives', 'canonical' and 'marginal' structures, and 'prototypes'
(e.g. Jackendoff, 1990). The documentation of usage of verb argument
structures, may shed considerable light on this division. Differentials
in production of argument structures by children over time may shed light
on the construction of underlying representations. These differences over
time appear to also have an effect on complexity of context sentences.
Production of tense, mood and negation markers appears to be contingent
on the stability of conceptual structures underlying production of
arguments. The current study supports the view that childrens'
conceptual structures can be characterized as prototypes, and that
gradual extension of structures is contingent on transition to new
prototypes. Early on (1968), Fillmore advocated the need for distinct
treatment of propositional and modal information. Our results show that
the presence of modality in a sentence is contingent on high-frequency
argument structures. If the development of modality (in Fillmore's sense)
and propositional content are distinguishable but show this relation, how is
it to be characterized? Jackendoff (1990) distinguishes between I-languages
(internal, based on innate predispositions) and E-languages (input-dependent).
He holds that truth-conditional semantics requires a theory of language
as an abstract artifact extrinsic to speakers. A possible interpretation of
our findings is that modality overlayed on propositional content may be the
means whereby this abstract artifact is reconstructed as part of a speaker's
internal representation. Truth-conditional semantics, then, involves
modelling mature inferential processes, or mature representation. This
possibility will be examined in light of actual developmental sequences, where
modal forms can be shown to emerge gradually to condition verb meaning
in ways at least reminiscent of model theoretic semantics.
JOHN KOUNIOS and PHILLIPS HOLCOMB
"Inferring Semantic-Memory Structure from Behavioral and Electrophysiological
Measures"
Researchers have investigated the structure of semantic-memory
representations by examining subjects' performance in tasks in which
they must judge the truth of sentences relating familar categories
(e.g., _ALL DOGS ARE ANIMALS_., or _SOME PEOPLE ARE TREES_.).
Differences in time to verify various classes of sentences were initally
interpreted in terms of characteristics of the semantic representations
retrieved from memory. Subsequent investigators have reinterpreted
these findings in terms of characteristics of the verification
_processes_ operating on these representations, rather than in terms of
the representations themselves. We have taken a different approach.
Instead of inferring the nature of knowledge representations based on
how people _use_ them (i.e., "behavioral" response date), we have been
investigating electrical protentials in the brain during sentence
verification. A certain component of these potentials seems to reflect
the _access_ or _retrieval_ of the stored knowledge, and not the
processes that use this information to judge truth. These
access/retrieval mechanisms better reflect structural characteristics of
semantic memory than do behavioral measures, yielding a different
picture of semantic-memory structure.
VINOD GOEL
"Specifying Classifying Representational Systems: A Critique and Proposal for
Cognitive Science"
Much of the work in cognitive science presupposes a theory of
representation complete with a classification scheme; a scheme which
allow us to say that two representations are interestingly similar or
interestingly different for particular purposes.
It is argued that such a scheme needs to meet at least the following
eight constraints:
(i) It must be grounded in some intuitions or a discipline-specific theory;
(ii) It must not beg the crucial questions;
(iii) It must result in an interesting number of categories (i.e.,
something other than a unit or infinite number);
(iv) It must individuate on the basis of relevant/constitutive
properties of symbol systems;
(v) It must be readily applicable;
(vi) It must be widely applicable;
(vii) The distinctions must be detectable by our behavioral data and
methodology;
(viii) It must be compatible with the computational story of mind.
The most widely used apparatus for classifying symbol systems is that of
informational and computational equivalence. This is critiqued and
found wanting on most accounts. A diagnosis of the problem is offered.
Time permitting, some prescriptive suggestions will also be made.
STEVEN HORST
"Notions of Representation and the Diverging Interests of Philosophy and
Empirical Science"
Contemporary discussions of mental representation often seem to assume that
there is a single sense of the word `representation' that (a) is applied
univocally to such disparate objects as pictures, maps and symbols, (b) is
utilized by empirical researchers in cognitive science, and (c) can readily be
used to provide a philosophical account of intentionality. In fact, however,
the notion of "representation" is paradigm-driven, and all of the familiar
paradigms (symbols, etc.) are convention- or interpretation-dependent. This
undercuts one philosophical strategy for explaining the content of mental
states in representational terms. However, a non-conventional notion of
"representation" as a theoretical term can be developed which seems to capture
the empirical scientist's needs even if it does not explain the intentionality
of mental states. This accords well with the following view of the importance
of the computer paradigm: that what it provides is (i) a formalism for the
mathematization of psychology and (ii) suggestive strategies for
microexplanation.
JOHN F. SOWA:
"Logic Foundations for Representing Object-Oriented Systems"
Systems of logic that have equivalent expressive power may have very
different structure. Short, simple statements in one system can often
be expressed only by awkward circumlocutions in another. During the
last quarter of the nineteenth century, three complete systems of
first-order logic were developed: Frege's Begriffsschrift, Peirce's
linear form of predicate calculus, and Peirce's existential graphs.
This talk compares the structures of propositions stated in these
systems to one another and to the underlying semantic structures of
language. Of the three, existential graphs have the most direct
translations to natural language. Remarkably, they are isomorphic
to Kamp's discourse representation structures that were independently
developed over 80 years later. They also form the logical foundation
for conceptual graphs, which are based on research on semantic
networks in artificial intelligence. Although Peirce's linear notation
has proved to be a powerful tool for foundational studies in mathematics,
his existential graphs seem better suited to studies of language.
[Note: This is the abstract of Sowa's oral presentation; the written
version differs somewhat.]
BARBARA L. SPEICHER
"Disentangling Conceptual and Linguistic Knowledge"
Language is the principal mediator of thought and one of the few vehicles with
which to explore abstract conceptual structures. Cognitive psychologists use
linguistic evidence to study psychological functions such as memory and
categorization and to construct models of knowledge representation. However,
researchers in cognitive psychology seldom address how to disentangle
conceptual and linguistic knowledge. In fact, the field seems to assume that
the two systems are isomorphic. The related field of neurology provides
insights into the relationship between cognition and language. Findings from
both split-brain and aphasic populations encourage a separation of linguistic
and conceptual structures. Specifically, Antonio Damasio's neurological theory
of convergence zones is presented and used to explain the differential
cognitive and linguistic abilities of neurologically impaired individuals
such as split-brain populations and aphasic populations. The paper analyuzes
both simple concepts and complex conceptual structures known as scripts.
BARBARA ABBOTT and LARRY HAUSER
"Natural Language and Thought"
Hauser defends the proposition that our languages of thought are public
languages. One group of arguments points to the coincidence of clearly
productive thought with overt possession of recursive symbol systems. Another
group relies on phenomenological experiences of mental discourse and making
thoughts physical. A third group cites practical considerations, e.g. Occam's
razor and the `streetlight principle' (look under the lamp) motivating looking
for instantiations of outer languages in thought first.
Abbott points to the literature and adduces a number of specific replies to
Hauser. Examples of productive behavior showing that natural language is not
necessary for productive thought include problem solving by chimpanzees, dreams,
and feral human cases (Genie). On phenomenological and practical grounds,
Abbott argues that communication of thoughts should be trivial if the inner
language is the outer language, but it is not; the decryption analogy Hauser
uses to apply the `streetlight principle' is flawed; and Occam's razor doesn't
cut any ice with Mother Nature.
MICHAEL TARR
"Behavioral and Computational Constraints in Human Shape Representation"
Do visual representations use an object-centered or viewer-centered
reference frame? Studies suggest that recognition is
orientation-dependent under many circumstances. The resulting theory,
Multiple-Views-Plus-Transformations, hypothesizes that recognition is
achieved by using a mental transformation to match input shapes to
object representations in a viewer-centered reference frame. Moreover,
these representations are orientation-specific, e.g. "views", and are
stored according to the frequency of occurrence of an object in a
particular orientation. However, familiarity is not the only factor
that determines represented views. First, there is evidence that views
are contingent upon the frequency with which other objects appear at
particular orientations. Representations of familiar objects in novel
views may arise as a result of the frequent appearance of an object's
visually similar cohorts. Second, there is evidence that views are
contingent upon the geometry of an object. The likelihood of a
representation arising increases with the distinctiveness of visible
surfaces at each orientation -- novel orientations are likely to be
represented to the extent that their geometry is unique, while
orientations in which the geometry differs only slightly from that
depicted in preexisting views are unlikely to be represented.
WHITMAN RICHARDS
"Is Perception for Real?"
What is the relation between the "external" world and our
conceptualization of this world? At one extreme an independent
external reality is denied, whereas at the other, an external reality
is a requirement for any conceptualization. Perception lies at the
heart of this controversy: can our percepts really reflect (or
approximate) the true structure of the world independent of our
observations or not? To address this question we need a clear
understanding of just what a percept is and what it entails. I offer
one definition and provide support for this choice using examples from
vision (Jepson & Richards 1991). For our percepts to be useful,
enabling us to predict the consequences of events and actions, certain
conditions must be met. Two I will discuss are (1) the ability to
manipulate representations or internal models, and (2) criteria for
data (observations) which generate reliable interpretations. This
second condition imposes limitations on the scope of useful percepts,
and shows that percepts (perhaps like scientific theories?) are
critically dependent upon a matching of cognitive concepts to modal
regularities in the world.
K. N. LEIBOVIC
"Brain Mechanisms for Perceptual Representation"
The brain is designed on a pattern of converging and diverging fiber
tracts with their associated broadly tuned receptive and responsive
fields. This puts certain constraints on the processing, transmission
and representation of information. The properties of perceptive fields
and target cells are taken as neural analogs of cognitive and logical
operations. Analysis and synthesis can then be carried out in
parallel; and the neural representations of elementary constituents
and categorical constructs can be grounded in associational programs
of activity in groups of cells.
------------------------------
End of NL-KR Digest
*******************
