... error-driven pruning formachinelearning of
coreference rules. In Proc. of EMNLP, pages 55–62.
V. Ng and C. Cardie. 2002b. Improving machine learn-
ing approaches to coreference resolution. In Proc. ... 104–111.
J. R. Quinlan. 1993. C4.5: Programs for Machine
Learning. Morgan Kaufmann.
W. M. Soon, H. T. Ng, and D. Lim. 2001. A machine
learning approach to coreferenceresolution of noun
phrases. Computational ... 2003. Coref-
erence resolutionusing competitive learningapproach.
In Proc. of the ACL, pages 176–183.
D. Zelenko, C. Aone, and J. Tibbetts. 2004. Coreference
resolutionfor information extraction....
... to coreference resolution. In Proceed-
ings of the 40th Annual Meeting of the Association
for Computational Linguistics (ACL), pages 104–111,
Philadelphia.
V. Ng. 2005. Machinelearningforcoreference ... 65.4 63.5
Table 4: Results of different systems forcoreference resolution
examined the C4.5 algorithm
4
which is widely used
for the coreferenceresolution task. The first line of
the table shows ... Powell”, and therefore refers to a male
person and cannot co-refer with “she”.
The entity-mention model based on Eq. (2) per-
forms coreferenceresolution at an entity-level. For
simplicity, the...
... application-internal representations
to a suitable format for several machine learning
toolkits: One module exposes the functionality of
the the WEKA machinelearning toolkit (Witten
and Frank, 2005), ... using it as a platform
for research including the use of new information
sources (which can be easily incorporated into the
coreference resolution process as features), different
resolution algorithms ... decision trees
for coreference resolution. In Proc. IJCAI 1995.
Morton, T. S. (2000). Coreferencefor NLP applications. In
Proc. ACL 2000.
Moschitti, A. (2006). Making tree kernels practical for natural
language...
... en-
tity. Coreferenceresolution on text datasets is well-
studied (e.g., (Cardie and Wagstaff, 1999)). This
prior work provides the departure point for our in-
vestigation of coreferenceresolution ... documents.
Evaluation metric Coreferenceresolution is of-
ten performed in two phases: a binary classifi-
cation phase, in which the likelihood of corefer-
ence for each pair of noun phrases ... 352–359,
Prague, Czech Republic, June 2007.
c
2007 Association for Computational Linguistics
Conditional Modality Fusion forCoreference Resolution
Jacob Eisenstein and Randall Davis
Computer Science...
... expressions is given in Table 1.
2.2 Learning Algorithm
For learningcoreference decisions, we used a
Maximum Entropy (Berger et al., 1996) model.
Coreference resolution is viewed as a binary clas-
sification ... of machinelearning based
coreference resolution systems (Soon et al., 2001;
Ng & Cardie, 2002; Kehler et al., 2004, inter alia).
Similarly, many researchers have explored tech-
niques for ... Germany
http://www.eml-research.de/nlp/
Abstract
Extending a machinelearning based coref-
erence resolution system with a feature
capturing automatically generated infor-
mation about semantic roles improves its
performance.
1 Introduction
The...
... used to build a
machine learning process. The notion of observing data, learning from it, and then
automating some process of recognition is at the heart of machinelearning and forms
the primary ... exploring machinelearning with
R! Before we proceed to the case studies, however, we will review some R functions
and operations that we will use frequently.
R Basics forMachine Learning
As ... message that is printed when you draw the
R forMachineLearning | 19
www.it-ebooks.info
With the function defined, we will use the lapply function, short for “list-apply,” to
iterate this function...
... increases in F-measure for both classi-
fiers and both data sets. When using RIPPER, for
example, performance increases from 64.3 to 67.2
for the MUC-6 data set and from 60.8 to 63.2 for
MUC-7. Similar, ... Unfortunately, the hand-selected
features precipitate a large drop in precision for pro-
noun resolutionfor the MUC-7/C4.5 data set. Ad-
ditional analysis is required to determine the reason
for ... improve precision on common noun
resolution. Overall, the learning framework and lin-
guistic knowledge source modifications boost per-
formance of Soon’s learning- based coreference res-
olution approach...
... Association for Computational Linguistics.
Simon Tong and Daphne Koller. 2002. Support vec-
tor machine active learning with applications to text
classification. Journal of MachineLearning Re-
search ...
Number of Foreign Words Annotated
BLEU Score
Number of Foreign Words Annotated
the approx. 54,500 foreign words
we selectively sampled
for annotation
cost = $205.80
last approx. 700,000
foreign ... preference
for covering frequent n-grams before covering in-
frequent n-grams. The VG method is depicted in
Figure 2.
Figure 3 shows the learning curves for both
jHier and jSyntax for VG selection...
... 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 only for CFG rules but also for other
characteristics ... 850–857,
Sydney, July 2006.
c
2006 Association for Computational Linguistics
Trimming CFG Parse Trees for Sentence Compression Using Machine
Learning Approaches
Yuya Unno
1
Takashi Ninomiya
2
Yusuke ... cre-
ate a compression forest as Knight and Marcu did.
We select the tree assigned the highest probability
from the forest.
Features in the maximum entropy model are de-
fined for a tree node and...
... (Daelemans et al., 2004) for Memory-
Based Learning, the MaxEnt Toolkit (Le, 2004)
for Maximum Entropy and LIBSVM (Chang and
Lin, 2001) for Support Vector Machines. For
TiMBL we used k nearest ... performance
for gold-standard trees
scoring 89.34% on accuracy and 86.87% on f-
score. The learning curves for the three algo-
rithms, shown in Figure 4, are also informative,
with SVM outperforming ... memory-based learning to
perform various graph transformations. One of the
transformations is node relabelling, which adds
function tags to parser output. They report an f-
score of 88.5% for the...
... 25–32,
Prague, Czech Republic, June 2007.
c
2007 Association for Computational Linguistics
Transductive learningfor statistical machine translation
Nicola Ueffing
National Research Council Canada
Gatineau, ... relevant for translating the new data are
reinforced. The probability distribution over the
phrase pairs thus gets more focused on the (reliable)
parts which are relevant for the test data. For an ... Semi-supervised training
for statistical word alignment. In Proc. ACL.
S. Nießen, F. J. Och, G. Leusch, and H. Ney. 2000. An
evaluation tool formachine translation: Fast evalua-
tion for MT research....
... Pittsburgh
{jsa8,hwa}@cs.pitt.edu
Abstract
Recent studies suggest that machine learn-
ing can be applied to develop good auto-
matic evaluation metrics formachine trans-
lated sentences. This paper further ana-
lyzes aspects of learning ... criteria. Machinelearning af-
fords a unified framework to compose these crite-
ria into a single metric. In this paper, we have
demonstrated the viability of a regression approach
to learning ... and Chris Brockett.
2001. A machinelearning approach to the automatic eval-
uation of machine translation. In Proceedings of the 39th
Annual Meeting of the Association for Computational Lin-
guistics,...
... with machine
learning algorithms that perform classification, clustering and pattern induction
tasks.
• Having a good annotation scheme and accurate annotations are critical for machine
learning ... that this is where you start for
designing the features that go into your learning algorithm. The better the features, the
better the performance of the machinelearning algorithm!
Preparing ... particular problem or phenomenon that has sparked
your interest, for which you will need to label natural language data for training for
machine learning. Consider two kinds of problems. First imagine...
... 2005.
c
2005 Association for Computational Linguistics
Using Emoticons to reduce Dependency in
Machine Learning Techniques for Sentiment Classification
Jonathon Read
Department of Informatics
University ... language-style dependency.
Also, note that neither machine- learning model
consistently out-performs the other. We speculate
that this, and the generally mediocre performance of
the classifiers, is due (at ... best-
performing settings for the Na
¨
ıve Bayes classifier
was a window context of 130 tokens taken from the
largest training set of 22,000 articles. Similarly, the
best performance for the SVM...
... T¨uba-
D/Z will show whether the performance achieved
for the HTC test set is scalable.
For future versions of the system, it might also
resolution (no values were given for pronouns).
Although a number ... learner is thus forced to
concentrate on difficult examples.
Although boosting has not yet been applied
to coreference resolution, it has outperformed
stateof-the-art systems for NLP tasks such ... described in this pa-
per.
(McCarthy and Lehnert, 1995) were among
the first to use machinelearningfor coreference
resolution. RESOLVE was trained on data from
MUC-5 English Joint Venture (EJV)...