... performing these tasks. In general we
can say that the use of structural features can im-
prove the performance of NLP tasks that require the
details of the contents to perform the task.
Most of ... successfully applied to
tasks in naturallanguageprocessing (NLP). Espe-
cially, state -of- the-art performance can be achieved
with kernel methods, such as Support Vector
Machine (Cortes and Vapnik, ... ker-
nels, are advantageous for both the concept and ac-
curacy of many naturallanguageprocessing (NLP)
tasks. Experiments have, however, shown that the
over-fitting problem often arises when these...
... tests for machine
translation evaluation. In Proceedings of the 2004 Confer-
ence on Empirical Methods in NaturalLanguage Processing
(EMNLP-04).
Alex Kulesza and Stuart M. Shieber. 2004. A learning ... in
the flexibility of the learning framework, which al-
lows for new features to be added. Moreover, adap-
tive learningmethods may be applicable if a small
sample of outputs of some representative ... and Chris Brockett.
2001. A machinelearning approach to the automatic eval-
uation ofmachine translation. In Proceedings of the 39th
Annual Meeting of the Association for Computational Lin-
guistics,...
...
"comprehension" ofnaturallanguage texts by computer.
That
Is, we were primarily
concerned
with the
introduction
of
stereotyplc
knowledge of objects into
the conceptual analysis of
text. ...
eliminated.
OPUS makes use of a well structured set of memory
associations for objects, the Object Primitives, to
encode Information
which
can be used
in a variety
of
Rleger's
qeneral ... kinds of associative
memory required to produce what appeared from Rieger's
model to ~e the "tremendous amount of
'hidden'
computation" necessary for the processing of...
... method) for handling incoming
messages of its instances. A class inherits methodsof its
superclasses.
Z. Interpretation of PAL Expressions in
Object-Oriented Domain
A class is defined for each ...
result of the evaluation is a new version of the
object runs0, say runs 1.
The above discussion is overly simplified for the purpose of
explanation. The following sections discuss a number of ... evaluating the form
which results from replacing each constant of a given PAL
expression by an instance of an object whose class name is the
same as the label of the constant. The evaluation is...
... Web Text Corpus forNaturalLanguage Processing
Vinci Liu and James R. Curran
School of Information Technologies
University of Sydney
NSW 2006, Australia
{vinci,james}@it.usyd.edu.au
Abstract
Web ... vectors of headwords in the corpus
to determine the most similar terms.
6.2 Evaluation
The evaluationof a list of synonyms of a target
word is subject to human judgement. We use the
evaluation ... performed a wide
range of NLP tasks using web data by querying
Altavista and Google. This included variety of
generation tasks (e.g. machine translation candi-
date selection) and analysis tasks...
... Because of the
high-dimensional nature ofnatural language, it is
often easy to generate an extremely large number of
features. The challenge of parameter estimation is
to find a combination of ... Republic, June 2007.
c
2007 Association for Computational Linguistics
A Comparative Study of Parameter Estimation Methodsfor
Statistical NaturalLanguageProcessing
Jianfeng Gao
*
, Galen Andrew
*
, ... compared five of the most competitive para-
meter estimation methods on four NLP tasks em-
ploying a variety of models, and the results were
remarkably consistent across tasks. Three of the
methods...
... even more difcult for them to
obtain healthcare due to isolation. Distance learning
provides an option of decreased isolation, but this
Evaluation of Distance Learningfor Health Education
Kelley ... the two
sites returning evaluation forms.
Study limitations include the fact that only seven sites
continue to make use of the distance learning sessions,
Evaluation
of program
effectiveness ... lack of healthcare providers
in rural areas, a lack of trust in western medicine and
a general lack of understanding of health issues. In
addition, since people with the least resources often...
... Ker-
nel methodsfor relation extraction. Journal of Machine
Learning Research.
Dell Zhang and Wee Sun Lee. 2003. Question classifica-
tion using support vector machines. In
proceedings of SI-
GIR’03, ... (production
of( n
1
) > production of( n
2
))
then n
2
= extract(L
2
);
else if (production
of( n
1
) < production of( n
2
))
then n
1
= extract(L
1
);
else
while (production
of( n
1
) == production of( n
2
))
while ... roles
associated with verbal predicates, for a total of
37,948 arguments. We randomly selected 30% of
sentences for testing and 70% for training. Addi-
tionally, 30% of training was used as a validation-
set....
... Computational Theory of Prose Style
for NaturalLanguage Generation
David D. McDonald and James D. Pnstejovsky
Department of Computer and Information Science
University of M~,=.~chnsetts at ... looked at our treatment of four of the
five points which we said at the onset of this paper had to
b,~ considered by any theory of prose style. The fifth
point, the kinds of information stylistic ... (1985a) WAGs as a
Grammatical Formalism for Generation", pr~eedings of
the 23rd Annual Meeting of the Association for
Computational Linguistics, University of Chicago.
McDonald D. & Pustejovsky...
... EMPIRICAL STUDIES OF DISCOURSE REPRESENTATIONS
FOR NATURALLANGUAGE INTERFACES
Ntis Dahlb~ick Ame JOnsson
Natural LanguageProcessing Laboratory
Department of Computer and Information Science ... future only be able to handle a subset of
natural language. The usability of this type of in-
terfaces is therefore dependent on finding subsets
of naturallanguage that can be used without the ...
Tennant, H. (1981) EvaluationofNatural
Language Processors Ph.D. Thesis, University of
Illinois at Urbana-Champaign.
Thomas, J.C. (1976)
A
method for studying
natural language dialogue....
... Califf and R. J. Mooney. 2004. Bottom-Up Rela-
tional Learningof Pattern Matching Rules for Infor-
mation Extraction. Journal ofMachineLearning Re-
search, MIT Press.
W. Drozdzynski, H U.Krieger, ... use PI for Person_In,
PO for Person_Out, POS for Position and ORG for
Organisation. In our experiments, we attempt to
investigate the influence of the size of the seed and
the size of the ... seeds for the next
iteration of the learning cycle. The cycle termi-
nates when no new relations can be acquired.
The linguistic annotation is responsible for en-
riching the natural language...
... In Proceedings of the First Conference of
the Association forMachine Translation in the Ameri-
cas, pages 193–205, Columbia, Maryland.
BLEU: a Method for Automatic EvaluationofMachine Translation
Kishore ... judges
which substitutes for them when there is
need for quick or frequent evaluations.
1
1 Introduction
1.1 Rationale
Human evaluations ofmachine translation (MT)
weigh many aspects of translation, ... output of Chinese-
English MT systems.
References
E.H. Hovy. 1999. Toward finelydifferentiated evaluation
metrics formachine translation. In Proceedings of the
Eagles Workshop on Standards and Evaluation, ...