Find:
Searching for domain specific learning w/2 grammatical structure w/2 musical and phonological sequences.
Restrict to:   Header   Title   Order by:   Expected citations   Hubs   Usage   Date   Try:   Google (CiteSeer)   Google (Web)   Yahoo!   MSN   CSB   DBLP
No documents match Boolean query. Trying non-Boolean relevance query.
500 documents found. Order: relevance to query.

Parser Evaluation: Using a Grammatical Relation Annotation.. - Carroll, Minnen, Briscoe (2003)   (Correct)   (2 citations)
and has been used to mark up a new public-domain corpus of naturally occurring English text. We
con- figurations" and also mapping onto a specific constituent structure. No specific annotation
as: A, press reportage G, belles lettres and J, learned writing. Genre has been found to affect the

treebank.linguist.jussieu.fr/./pdf/17.pdf

Automatic Generation of Programs with Grammatical Evolution - O'Neill, Ryan   (Correct)
applied to a number of diverse problem domains such as symbolic regression [9]finding
with Genetic Programming (GP) 4]GE takes a BNF specification of a language, or subset thereof, from
Automatic Generation of Programs with Grammatical Evolution Michael O'Neill &Conor Ryan Dept.

scare.csis.ul.ie/michael/papers/aics99.ps.gz

Crossover in Grammatical Evolution: A Smooth Operator? - O'Neill, Ryan (2000)   (Correct)
superior to the other operators on both problem domains. We will now describe the results for each
Algorithms in Search, Optimization and Machine Learning. Addison Wesley. 5. Koza, J. 1992. Genetic
Crossover in Grammatical Evolution: A Smooth Operator? Michael O'Neill

shine.csis.ul.ie/papers/eurogp2000.ps.gz

Evolving Multi-line Compilable C Programs - O'Neill, Ryan (1999)   (Correct)   (3 citations)
this system, GE has been applied to other problem domains, and during this time GE has undergone some
nucleotides in a codon, 61 of these coding for a specific Amino Acid, the other three are special codons
to compare the performance of GE to other learning methods over some problem domains. The original

scare.csis.ul.ie/michael/papers/eurogp99.ps.gz

Extracting Usability Information from User Interface Events - Hilbert, Redmiles (1999)   (Correct)   (15 citations)
the problem of analyzing sequential data in other domains, this paper primarily focuses on techniques that
that have in fact been brought to bear on the specific problems associated with analyzing HCI events.
associated with these five usability attributes: Learnability: The system should be easy to learn so

www.ics.uci.edu/~dhilbert/papers/acmcs/revised.pdf

A Constraint-based and Head-driven Analysis of Multiple Nominative.. - Kim (2000)   (Correct)
are in di#erent local trees. Without expanding the domain of locality, it is di#cult to state what license
one: 3 3 The sentence is grammatical with a `specific' reading. 17) Etten salam-i apeci-ka
of argument composition (cf. Chung 1998)2 Grammatical Properties of Nominative Phrases 2.1 Are They

cslipublications.stanford.edu/HPSG/1/hpsg00kim.ps

Crossover in Grammatical Evolution: The Search Continues - O'Neill, Ryan, Keijzer.. (2001)   (Correct)
Grammatical Evolution is essential on the problem domains examined. The mechanism of one-point crossover
Algorithms in Search, Optimization and Machine Learning. Addison Wesley. 5. Keijzer M.Ryan C.O'Neill
Crossover in Grammatical Evolution: The Search Continues Michael

shine.csis.ul.ie/papers/eurogp2001.ps.gz

Grammatical Assimilation - Briscoe   (Correct)
1996)Bayesian learning theory is a general domain-independent formulation of learning. The most
By a LAD, I mean nothing more or less than a learning mechanism which incorporates some language-speci

www.cl.cam.ac.uk/~ejb/ga-review.ps.gz

Learning to Understand - Tellier (1998)   (Correct)
Set, useful further, is ours. First, a semantic domain has to be defined. Let us note it D. Definitions
1 Learning to Understand Isabelle Tellier LIFL and
This framework integrates recent results on grammatical inference with positive structural examples

www.grappa.univ-lille3.fr/ftp/reports/tellierml.ps

A Lexical-Functional Analysis of Predicate Topicalization in .. - Webelhuth, Ackerman   (Correct)
in these, primarily lexicalist, theories different domains of grammar are factored into different levels
in the original formulation of this principle: specifically, we suggest that the proposed repertoire of
that topicalized elements share values with the (grammatical) function status of an entity an indeterminate

ling.ucsd.edu/~ackerman/glac.pdf

A Genetic Algorithm for Finite State Automata Induction with.. - Belz, Eskikaya   (Correct)
be copies of a parent with one gene mutated. 2.2 Domain-speci c GA Techniques Representation of Automata
L. G. Valiant. 1989. Cryptographic limitations on learning boolean formulae and nite automata. In
by A, denoted L(A)is fxj(s 0 x) 2 Fg. 1.2 Grammatical Inference from Positive Data Generally, the

ftp.cogs.sussex.ac.uk/pub/nlp/a.belz/papers/aGeneticAlgorithm.ps

Toward Korean Text-to-Sign Language Translation System(TeST) - Kang, Park   (Correct)
are working on R&D of HCI which aim at specific kinds of handicapped people like Text to Voice
is an agglutinative language which functions grammatically as grammatical morpheme which expresses
into morphemes suitable to sign language structure. STEP 2: The system searches sign language

www.links.nectec.or.th/pub/NLPRS/paper/mtmd4p.ps.gz

Genetic Code Degeneracy: Implications for Grammatical.. - O'Neill, Ryan (1999)   (Correct)   (3 citations)
of degeneracy in the genetic code for the problem domains addressed here. 1 Introduction Grammatical
terminals associated with GP [3]GE takes a BNF specification of a language, or subset thereof, from
Genetic Code Degeneracy: Implications for Grammatical Evolution and Beyond Michael O'Neill &Conor

shine.csis.ul.ie/papers/ecal99.ps.gz

Confidence Measures Derived From An Acceptor HMM - Williams, Renals (1998)   (Correct)   (1 citation)
must be comparable across utterances. More specifically, an acoustic confidence measure is one which
on BN data relative to that for the more grammatically constrained NAB data. An explanation linking
k )is computed by rescoring the Viterbi state sequence using the local posterior probability estimates

ftp.dcs.shef.ac.uk/share/spandh/pubs/williams/icslp98_conf.ps.gz

Mathematical Aspects of Command Relations - Kracht   (Correct)   (7 citations)
[ Reinhart, 1981 ]the beginning of the study of domains. Moreover, Koster, 1986 ]presents a
{ if given in that format {is possible. 2 Grammatical Relations on Trees 2.1 De nitions A tree is
Abstract In gb, the importance of phrase-structure rules has dwindled in favour of nearness

ftp.math.fu-berlin.de/pub/usr/kracht/sprache/acl93.ps

Corpus Analysis for Revision-Based Generation of Complex.. - Jacques Robin (1993)   (Correct)   (4 citations)
floating content units cannot be ignored. In our domain, they account for over 40% of lead sentence
of sentence 1 into sentence 2 in Fig. 6 is a specific Adjunctization example: to score" is replaced
this constituent: 1) semantic content 2 2) grammatical function, 3) structural status (i.e. head,

ftp.di.ufpe.br/pub/users/jr/aaai93.ps.gz

Constants of Grammatical Reasoning - Moortgat (1999)   (Correct)   (2 citations)
nature, stateable within the subcategorizational domain of lexical items. Non-local dependencies
more logical constants become distinguishable. Specifically, it becomes possible to identify logical
Constants of grammatical reasoning Michael Moortgat Contents

www.let.uu.nl/%7EMichael.Moortgat/personal/Courses/constants.pdf

Generating Random Binary Trees - A Survey - Mäkinen (1998)   (Correct)   (1 citation)
approach are not considered in this paper. 2 Grammatical methods There are several coding methods for
the strings of balanced parentheses and Zaks' sequences. Mairson #9# gives a general method for
in preorder to obtain the code word. The Zaks' sequence of the sample tree shown in Figure 2 is

www.cs.uta.fi/reports/pdf/A-1998-3.pdf

Towards Semantic-Based Overlap Measures for Question Answering - Molla   (Correct)
of methodologies that rely on world knowledge or domain knowledge. Thus, we have refrained from testing
of interference from other modules. Following the specifications of the QA track of TREC8 to TREC10, the
information, and to that end they incorporate grammatical relations and flat logical forms. A full

www.comp.mq.edu.au/~diego/publications/altw03_gr_mlf.pdf

First Year Report - Mathlang Framework For (2003)   (Correct)
content. It does not restrict the mathematical domain in question and it does not direct the author to
.11 4.2 Grammatical categories .
more formal information such as formulae or text structures (theorems, examples,Use of encoded

www.macs.hw.ac.uk/~mm20/papers/Maarek:phd_first_year_report-2003-aug.ps.gz

First 20 documents  Next 20

Try your query at:   Google (CiteSeer)   Google (Web)   Yahoo!   MSN   CSB   DBLP

CiteSeer.IST - Copyright Penn State and NEC