... wisely integrate indications for entailment,
probabilistic methods have the advantage of be-
ing extendable and enabling the utilization of well-
founded probabilistic methods such as the EM algo-
rithm.
We ... certain model-
ing aspects that need to be improved.
2 Probabilistic Model
Under the lexical entailment scope, our modeling
goal is obtaining a probabilistic score for the like...
... Determining Word Sense Dominance Using a Thesaurus
Saif Mohammad and Graeme Hirst
Department of Computer Science
University of Toronto
Toronto, ... of
that sense in text. We propose four new
methods to accurately determine word
sense dominance using raw text and a pub-
lished thesaurus. Unlike the McCarthy
et al. (2004) system, these methods ... the need for a similarly-sense-
distributed...
... 81–84,
Suntec, Singapore, 4 August 2009.
c
2009 ACL and AFNLP
Realistic Grammar Error Simulation using Markov Logic
Sungjin Lee
Pohang University of Science and
Technology
Pohang, Korea
junion@postech.ac.kr ... grammar errors. The ap-
proach is based on Markov logic, a representa-
tion language that combines probabilistic graphi-
cal models and first-order logic (Richardson and
D...
... inducing semantic classes
for German verbs. Using probability
distributions over verb subcategorisation
frames, we obtained an intuitively plausi-
ble clustering of 57 verbs into 14 classes.
The automatic ... hand-
constructed semantic verb classes. A
series of post-hoc cluster analyses ex-
plored the influence of specific frames and
frame groups on the coherence of the verb
classes, an...
... verb classes have
been identified. Associated with clustering
threshold 1.5 are 1421 verb classes, averaging
14.1 WordNet verb synsets. Associated with
clustering threshold 2.0 are 1563 verb classes,
averaging ... semantic verb classes. Section 3
summarizes the features of WordNet
(http://www.cogsci.princeton.edu/~wn) and
LDOCE (Procter, 1978) that support the
automatic induction of sem...
... describe a first
probabilistic extension to this framework, which
aims at modeling the different levels of the repre-
sentation (section 3). We test our model on parsing
the WSJ treebank using a re-ranking ... WFM) specified in equations
(2-4) and explained in the main text.
3 A probabilistic Model for TDS
This section describes the probabilistic generative
model which was implemented i...
... is the op-
timal recall (i.e., # optimal/# NEs). “# classes is
the number of distinct classes in a gazetteer, and
“# used” is the number of classes that were out-
put for the training set. Gazetteers ... NER.
3 Using Gazetteers as Features of NER
Since Japanese has no spaces between words, there
are several choices for the token unit used in NER.
Asahara and Motsumoto (2003) proposed...
... the children i are chosen only
among the committee members.
Generating committees using CBC works best
for classes with many members. In its original
application (Pantel and Lin 2002), CBC ...
WordNet 2.0 served as our testing ontology.
Using the algorithm presented in Section 4, we
induced ontological feature vectors for the noun
nodes in WordNet using the lexical co-occurrenc...
... Efficient probabilistic top-down and left-corner parsingt
Brian Roark and Mark Johnson
Cognitive and Linguistic ... explicit the relationships between
constituents required for partial interpretation.
The parser uses probabilistic best-first pars-
ing methods to pursue the most likely analy-
ses first, and a beam-search ... pending heap, and the category at the
top of its stack is...