... pronoun
ana npform NP form of the anaphor
ana gramrole grammatical role of the
anaphor
ana agr agreement of the anaphor
ana semclass* semantic class of the anaphor
ante npform NP form of the antecedent
ante ... 20)
same agr same agreement of anaphor
and antecedent?
same gramrole same grammatical role of
anaphor and antecedent?
same semclass* same semantic class of
anaphor and antecedent?
Table 1: Features ... system’s performance on
the manually annotated (gold standard) data with-
out the semantic features.
For the baseline, accuracy is significantly higher
for the gold standard data than for the two...
... ante
case grammatical case of antecedent
5. ante
s depth the level of embedding in a sentence
6. ana
gram func grammatical function of anaphor
7. ana
npform form of anaphor
8. ana
agree person, ... is based on the same as-
sumptions as the former. The information content of
a non-NP-markable is calculated as follows, based
on a set of 553 Switchboard dialogues: For each
word in the markable, ... language for
data analysis and graphics. Journal of Computational and
Graphical Statistics, 5:299–314.
Kohavi, Ron & George H. John (1997). Wrappers for fea-
ture subset selection. Artificial Intelligence...
... have
typically been dealt with as part of the syntax (but
cf. Kuno, Takami & Wu (1999) for an alterna-
tive approach) . Early generative treatments used a
WH-movement
transformation (McCawley, 1998)
to ... stage
4093/4242
=
96.5%
for other systems to which we can compare them.
We take this level of success as an indication of the
feasibility of our data-driven, modular approach.
Additionally, our approach has the advantage ... Statistical Mod-
els for Natural Language Parsing.
Ph.D. thesis,
University of Pennsylvania, Philadelphia, PA.
S. E. Fahlman. 1988. An empirical study of learning
speed in back-propagation networks....
... the Association forMachine Translation
in the Americas (AMTA-2006).
Christoph Tillmann, Stephan Vogel, Hermann Ney, Hassan
Sawaf, and Alex Zubiaga. 1997. Accelerated DP-based
search for statistical ... of the Association for
Computational Linguistics.
Simon Corston-Oliver, Michael Gamon, and Chris Brockett.
2001. Amachinelearningapproach to the automatic eval-
uation of machine translation. ... Evaluation with MachineLearning
A good automatic evaluation metric can be seen as
a computational model that captures a human’s de-
cision process in making judgments about the ade-
quacy and...
... 1998) and Snowball
(Agichtein and Gravano, 2000), because there is no
gold-standard evaluation corpus available. We
have adapted the evaluation method suggested by
Agichtein and Gravano, i.e., ... data
set. If at all possible, the training data should ex-
hibit a skewed distribution of reports to events.
Actually, such training data may be the only realis-
tic chance for reaching a large ... In Proc. of ACL-
03, pages 224–231, Sapporo, Japan.
R. Yangarber, R. Grishman, P. Tapanainen, and S. Hut-
tunen. 2000. Automatic Acquisition of Domain
Knowledge for Information Extraction. In...
... measured with an infrared gas
analysis system (Uras 3 G; Hartmann & Braun AG, Frank-
furt am Main, Germany). A whole-rosette cuvette design
was used as described in [31]. Gas exchange was ... Whereas many
tropical and subtropical species have only limited
capacities to cope with low temperature, plants from
temperate climates, such as Arabidopsis thaliana, grow
at low temperature and can ... acclimation in A. thaliana
FEBS Journal 278 (2011) 506–518 ª 2010 The Authors Journal compilation ª 2010 FEBS 509
A systems biology approachfor the analysis of
carbohydrate dynamics during acclimation...
... natural language are also
observed. For example, we improve MWE min-
ing result by EBP detection. Comparisons with
variant n-gram approaches, which are the leading
approaches, are performed for ... extraction, LCS approach
is applied with great efficiency and per-
formance guarantee. Experimental results
show that LCS-based approach achieves
better results than n-gram.
1 Introduction
Language ... extraction of MWE plays an important role
in several areas, such as machine translation (Pas-
cale,1997), information extraction (Kalliopi,2000)
etc. On the other hand, there is also a need
for...
... were annotated with
the types of financial transactions they are most
related to. Paragraphs that did not fall into a
category of interest were classified as “other”.
The annotated paragraphs ... etc.
133
Maytag: A multi-staged approach to identifying
complex events in textual data
Conrad Chang, Lisa Ferro, John Gibson, Janet Hitzeman, Suzi Lubar, Justin Palmer,
Sean Munson, Marc Vilain, and Benjamin ... semantic type of the
phrase (for named entities), the phrase vocabu-
lary, the distance to the target head, and local
context (words and phrases).
Our initial evaluation of this approach has
given...
... Meeting of the Association for Com-
putational Linguistics, Barcelona, Spain.
Bo Pang, Lillian Lee, and Shivakumar Vaithyanathan.
2002. Thumbs up? Sentiment Classification using
Machine Learning Techniques. ... that performance in a
given topic is best if the training data is from the
same topic. For example, the Finance-trained SVM
classifier achieved an accuracy of 78.8% against ar-
ticles from Finance, ... Third An-
nual Symposium on Document Analysis and Informa-
tion Retrieval, pages 161–175, Las Vegas, Nevada.
Kushal Dave, Steve Lawrence, and David M. Pennock.
2003. Mining the Peanut Gallery:...
...
Community-Based Health Education Intervention: A Service -Learning
Approach
Srijana M. Bajracharya, Associate Professor, Department of Health Promotion and Physical
Education, Ithaca College
A variety ... papers at the national conference
such as American Association of Health, Physical Education, Recreation, and Dance
(AAHPERD). Such presentations allow students to take maximum advantage of ... situation for all involved. For students, such experiential
learning can be most valuable and meaningful.
Evidence of participation in service -learning projects can be a valuable part of a
student’s...
... cross-checking Volker Wieland
21 2007 Corporate marginal tax rate, tax loss carryforwards
and investment functions – empirical analysis
using a large German panel data set Fred Ramb
x
t,i,j
j ... The marketability of bank assets and managerial Falko Fecht
rents: implications for financial stability Wolf Wagner
31
07 2008 Which interest rate scenario is the worst one fora bank? ... 23436383103
Maturity (months)
Change in interest rates (percentage points)
26
11 2007 Exchange rate dynamics in a target zone - Christian Bauer
a heterogeneous expectations approach Paul De Grauwe,...
... essential, as pattern-based approach is enhanced
with the supervised machine learning.
In this paper, we propose a novel approach to
automatic synonym identification based on super-
vised learning ... David Weir and Diana McCarthy. 2004.
Characterising Measures of Lexical Distributional
Similarity. Proc. of COLING 04, 1015–1021.
6
formalization of similarity-based approach would
be essential, ... 786–774.
Shachar Mirkin, Ido Dagan, and Maayan Geffet. 2006.
Integrating pattern-based and distributional similarity
methods for lexical entailment acquisition. Proc. of
COLING/ACL 06, 579–586.
Brian...
... give-cake big-cake …
Figure 1. Attribute-value vector for syntactic relations
Given that some types of information are not avail-
able for certain instances, many attributes will have
null values. ... only classified a few ex-
amples (form 1 to 6).
In Table 2 we show the accuracy of the theory
learned for each verb, as well as accuracy
achieved by two propositional machinelearning
algorithms ... a few are designed for specific applica-
tions, such as MT. Existing multilingual approaches
can be classified as (a) knowledge-based ap-
proaches, which make use of linguistic knowledge
manually...