... v
1
, y
i
, . . . , v
n
, y
n
} are given as input to the
ME classifier, which learns how to classify new
vectors v, corresponding to unseen pairs of sen-
tences S
1
, S
2
.
We use nine ... 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 ... can
be used to recognize paraphrases. They
all employ string similarity measures ap-
plied to shallow abstractions of the input
sentences, and a Maximum Entropy clas-
sifier to learn how to combine...
... 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. ... 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, ... of au-
tomatically acquiring LFG resources for Spanish
from Cast3LB. Machine- learning- based Cast3LB
tag assignment yields statistically-significantly
improved LFG f-structures compared to parser-
based...
... to the user
model), we would need to explore many more
strategies through interactions with users to find
an optimal one. One way to reduce costs for build-
ing such an optimised strategy is to ... lead to
repetitive action, i.e. if a screen output was once
shown to this user, and the user has previously
used or referred to the screen, the screen will be
used over and over again.
For learning ... generation and input leads
to more robust interaction (Oviatt, 2002) and re-
duced cognitive load (Oviatt et al., 2004). In this
paper we investigate the use of machine learning
(ML) to explore human multimodal...
... Us-
ing MachineLearning
Machine learning has been used successfully to
control a rule-based system that performs a dif-
ferent task, namely document filtering (Wolinski
et al., 2000). The learning ... the use of learning for NERC. In-
stead of using ML to construct a NERC system
that will be used autonomously, the system con-
structed by ML, according to our approach is
used to monitor the performance ... Using
Learning- based Filters to Detect Rule-based Filter-
ing Obsolescence. In Recherche d’ Information
Assistée par Ordinateur, RIAO, Paris, France,
pp.1208-1220.
Using MachineLearningto Maintain...
... 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...
... 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 coreference resolution of noun
phrases. Computational ... and error-driven pruning for machinelearning of
coreference rules. In Proc. of EMNLP, pages 55–62.
V. Ng and C. Cardie. 2002b. Improving machine learn-
ing approaches to coreference resolution. ... 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...
... now be used to generate, e.g.,
the string "Kim gives a table to Peter", as well as
the string "Noam donates a book to Peter".
However, it will not be able to generate a ... the adaption of
a NLG system to a particular use of a lan-
guage.
1 Introduction
In recent years, a MachineLearning tech-
nique known as Explanation-based Learning EBL
(Mitchell, Keller, ... used for parsing to automatically spe-
cialize a given source grammar to a specific domain.
In that case, EBL is used as a method for adapting a
general grammar and/or parser to the sub-language...
... analyze words into their
components (letters or radicals)
Learning to Read Chinese
(Van and Zian, 1962)
Starts with learningto read characters
Three stages
Relate sound/meaning to global shape ... predictor of
later English reading skills, but not in
Chinese
Knowledge of general information and
verbal memory is a good predictor of ability
to read Chinese and Japanese
Differences appear to ... variety
Chinese words are often two or more
morphemes, with no word boundaries
indicated
Chinese uses many more graphic units
Learnability of English and
Chinese
Is it harder to learn Chinese...
... (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 ... chart decoder
in C++. It generalizes over the dotted-product operator in
Earley style parser, to allow us to leverage many opera-
tors
¯
t ∈ T as above-mentioned, such as binarizations, at
different...
... 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...
... for German, we were able to obtain the
system submitted by (Curran and Clark, 2003) to
the 2003 CoNLL competition. In order to run the
recogniser, the data needs to be tokenised, tagged
and lemmatised, ... results support the intuition
that ensemble methods are superior to single clas-
sifiers.
To put the performance of our system into per-
spective, we established a baseline and an upper
bound for ... for pronoun resolution is
81.5. However, (Morton, 2000) only attempts to
resolve singular pronouns, and there is no mention
of what percentage of total pronouns are covered
by this restriction.
(Soon...
... types of extensions to the Soon et
al. corpus-based approach. First, we propose and
evaluate three extra-linguistic modifications to the
machine learning framework, which together pro-
vide substantial ... prohib-
ited by the Soon system.
5 Conclusions
We investigate two methods to improve existing
machine learning approaches to the problem of
8
Soon et al. (2001) present only the tree learned for ... RIPPER
parameters are set totheirdefaultvalue except that classification
rules are induced for both the positive and negative instances.
3 Modifications to the Machine Learning
Framework
This section...
... assumes the input to
her algorithm to be only referential pronouns. This
simplifies the task considerably.
7 Conclusions and Future Work
We presented a machinelearning approach to pro-
noun resolution ... (A3) has to
have access not only to (B2) but also to (A1).
3 Data
3.1 Corpus
Our work is based on twenty randomly chosen
Switchboard dialogues. Taken together, the dia-
logues contain 30810 tokens ... Applications, College Park, Md., 1999, pp. 47–52.
Soon, Wee Meng, Hwee Tou Ng & Daniel Chung Yong Lim
(2001). A machinelearning approach to coreference resolu-
tion of noun phrases. Computational Linguistics,...
... in-
terpretation of the sentence, and could contribute
to a natural language understanding or machine
translation application. Since WH dependencies
also tend to distort the surface subcategorization
properties ... A machine- learning approach to the identification of WH gaps
Derrick Higgins
Educational Testing Service
dchiggin@alumni.uchicago.edu
Abstract
In ... identifying gaps could also aid
in automatic lexical acquisition techniques. Many
other applications are imaginable as well, using
the gap location to inform intonation, semantics,
collocation frequency,...