... pages 27–35,
Suntec, Singapore, 4 August 2009.
c
2009 ACL and AFNLP
Paraphrase RecognitionUsingMachineLearningto Combine Similarity
Measures
Prodromos Malakasiotis
Department of Informatics
Athens ... order of the to-
kens maintained;
3
s
2
1
, s
2
2
: as in the previous case, but now the tokens are
replaced by their stems;
s
3
1
, s
3
2
: as in the previous case, but now the tokens are
replaced ... substitution
of a single token. Moreover, we use high-level
3
We use Stanford University’s tokenizer and POS-tagger,
and Porter’s stemmer.
4
Soundex is an algorithm intended to map English names
to alphanumeric...
... attributed to two main factors. Firstly,
the mapping from Cast3LB tags to LFG grammat-
ical functions is not one -to- one. For example three
Cast3LB tags (CC, MOD and ET) are all mapped
to LFG ADJUNCT. ... 136–143,
Sydney, July 2006.
c
2006 Association for Computational Linguistics
Using Machine- Learningto Assign Function Labels to Parser
Output for Spanish
Grzegorz Chrupała
1
and Josef van Genabith
1,2
1
National ... present paper we use a machine- learning ap-
proach in order to add Cast3LB function tags to
nodes of basic constituent trees output by a prob-
abilistic parser trained on Cast3LB. To our knowl-
edge,...
... cooperative learning, students have more
opportunities to talk and to share ideas. This interaction with groupmates
encourages students to restructure their ideas. For instance, they may need to
summarize, ... draft of their essays using ideas gathered during their research.
(Teacher may need to offer additional help to students who still have difficulty relating
their research to their essays' ... to find one person not in the class to read their story. The goal here is to
provide feedback on the clarity and affective impact of the text, as well as to educate others
about endangered...
... this
method to unsupervised learningto overcome the
lack of training data. However their model also
has the same problem. McDonald (McDonald,
2006) independently proposed a new machine
learning ... sentences some-
times do not correspond.
To solve the former problem, we apply a maxi-
mum entropy model to Knight and Marcu’s model
to introduce machinelearning features that are de-
fined not ... University of Tokyo
3
School of Informatics, University of Manchester
4
SORST, JST
Hongo 7-3-1, Bunkyo-ku, Tokyo, Japan
{unno, yusuke, tsujii}@is.s.u-tokyo.ac.jp
ninomi@r.dl.itc.u-tokyo.ac.jp
Abstract
Sentence...
... seeks to identify
a piece of text according to its author’s
general feeling toward their subject, be it
positive or negative. Traditional machine
learning techniques have been applied to
this ... by inde-
pendent trained annotators), each containing 100
stories. We trained a model on a dataset relating to
one topic and tested that model using the other top-
ics. Figure 1 shows the results ... train-
ing process. Other extensions of this work are to
collect more text marked-up with emoticons, and to
experiment with techniques to automatically remove
noisy examples from the training data.
Acknowledgements
This...
... redesign of AI systems to conform to new
knowledge is impractical, but machinelearning metho ds mightbe
able to trackmuchofit.
1.1.2 Wellsprings of Machine Learning
Workinmachine learning is nowconverging ... variables
Introduction toMachine Learning
c
1996 Nils J. Nilsson. All rights reserved.
INTRODUCTION
TO
MACHINE LEARNING
AN EARLY DRAFT OF A PROPOSED
TEXTBOOK
Nils J. Nilsson
Rob otics Lab oratory
Department ... Bibliographical and Historical Remarks
Tobeadded.
Every chapter
will contain a
brief survey of
the history of
the material
covered in that
chapter.
Introduction toMachine Learning
c
1996 Nils...
... and divide the points into slides. At the
same time, students need to take into consideration slide layout. A slide cannot be
too cluttered, the size of the font has to be large enough, and ... slide sorter.
Comparison to Writing with a Word Processor
The following generalizations apply to an instructional situation in which the writers are
learning how to write and can benefit from ... PowerPoint make it even more suitable than a word processor for
learning how to write at the lower levels of EFL. The tool is easy to learn and use. The
environment is friendly, attractive and...
... use machinelearning techniques to
eliminate non-comparative sentences from the
candidates. As a result, we achieved signifi-
cant performance, an F1-score of 88.54%, in
our experiments using ... final goal is to find an effective method to
extract S1 and S2, but single-keyword searching
just outputs S1 and S3. In order to capture S2, we
added long-distance-words sequences to the set ... Maximum
Entropy approach to National Language
Processing. In our experiments, we used Zhang’s
Maximum Entropy Model Toolkit (2004). Naïve
Bayesian classifier is used to prove the perfor-
mance...
... Lim. 2001. A machine
learning approach to coreference resolution of noun
phrases. Computational Linguistics, 27(4):521–544.
M. Strube and C. M¨uller. 2003. A machinelearning ap-
proach to pronoun ... Cardie. 2002b. Improving machine learn-
ing approaches to coreference resolution. In Proc. of
the ACL, pages 104–111.
J. R. Quinlan. 1993. C4.5: Programs for Machine
Learning. Morgan Kaufmann.
W. ... generate good can-
didate partitions. Given that machinelearning ap-
proaches to the problem have been promising, our
choices will be guided by previous learning- based
coreference systems, as described...
... (Section 3.3).
Using each of these as features, we use Support Vec-
tor Machines (SVM) to produce a combined real-
number grade. Finally, we build an Isotonic Regres-
sion (IR) model to transform ... abstract relations, then sightly more concrete
relations.
We define a total of 68 features to be used to train
our machinelearning system to compute node-node
(more specifically, subgraph-subgraph) matches. ... similar to those more commonly
used in the textual entailment community.
Specifically, we seek answers to the following
questions. First, to what extent can machine learn-
ing be leveraged to improve...
... pri-
vately moved into their scene. The director has no
visible indication that the matcher has clicked on
an object. However, the director needs to click the
Continue (next object) button (see Fig-
ure ... button (see Fig-
ure 1) in order to move the current target into the
director’s scene, and move on to the next target
object. This means that the players need to discuss
not just what the target ... which object is to be added next to the
scene. As the game proceeds, the next target ob-
ject is automatically determined by the interface
and privately indicated to the director with a blue
arrow,...
... 2008.
I. Fahmi and G. Bouma. 2006. Learningto iden-
tify definitions using syntactic features. In R. Basili
and A. Moschitti, editors, Proceedings of the EACL
workshop on Learning Structured Information ... containing 549
definitions and applied a grammar on it.
Machine learning was then applied to im-
prove the results obtained with the gram-
mar. Two machinelearning experiments
were carried out. In the ... a
verb (or verbal phrase) other than to be is used as
connector (e.g. to mean, to comprise). It also hap-
pens that a punctuation character is used as con-
nector (mainly :), such patterns are contained...
... grammar through
the proposed operators. This step is called populating,
using the proposed operators to find all relevant elemen-
tary trees γ which may have contributed to explain the
source span, ... (R
2
X
v
Y ))
Table 5: Operators for manipulating the trees
possible due to the many -to- many alignment, insertions
and deletions of terminals. So, we introduce the oper-
ators to remove the interior ... rule: X
1
X
2
→ X
1
X
2
. This operator is neces-
sary, we need a scheme to automatically back off to the
meaningful glue or Hiero-alike rules, which may lead to a
cheaper derivation path for constructing...