... nese translations appear in the aligned Chinese
sentence. For example, foran English occurrence
channel, both “频道” (sense 1 translation) and “途
径” (sense 5 translation) happen to appear ... bilingual translation lexicon.
Training of WSD Classifier
Much research has been done on the best super-
vised learning approach for WSD (Florian and
Yarowsky, 2002; Lee and Ng, 2002; Mihalcea and ... reduction is particularly sig-
nificant for the noun circuit. For this noun, the par-
allel corpora do not have enough training examples
for sense 4 andsense 5 of circuit, and these two
senses constitute...
... Daelemans, and A. van den
Bosch. 2002. Parameter Optimization for Machine-
Learning of WordSense Disambiguation. Natural
Language Engineering, Special Issue onWord Sense
Disambiguation Systems, ... mod-
ules (e.g. (Gale and Church, 1993; Ng et al., 2003;
Diab and Resnik, 2002; Chan and Ng, 2005; Da-
gan and Itai, 1994)) andfor WSD systems that use
a combination of existing WordNets with multilin-
gual ... forWordSense Disambiguation
Els Lefever
1,2
, V
´
eronique Hoste
1,2,3
and Martine De Cock
2
1
LT3, Language and Translation Technology Team, University College Ghent
Groot-Brittanni
¨
elaan...
... (Chan and
Ng, 2005b), using the same 6 English-Chinese
parallel corpora (Hong Kong Hansards, Hong
Kong News, Hong Kong Laws, Sinorama, Xinhua
News, and English translation of Chinese Tree-
bank), ... Proc. of SENSEVAL-2.
Yoong Keok Lee and Hwee Tou Ng. 2002. An empir-
ical evaluation of knowledge sources and learning
algorithms forwordsense disambiguation. In Proc.
of EMNLP02.
Diana McCarthy, ... disambiguate word
sense: An exemplar-based approach. In Proc. of
ACL96.
Hwee Tou Ng, Bin Wang, and Yee Seng Chan. 2003.
Exploiting parallel texts forwordsense disambigua-
tion: Anempirical study. ...
...
Massimiliano Ciaramita and Mark Johnson. 2004. Mul-
ti-component WordSense Disambiguation. Proceed-
ings of Senseval-3: 3rd International Workshop on
the Evaluation of Systems for the Semantic Analysis ... translation
for an ambiguous source word. There is not always
a direct relation between the possible senses for a
word in a (monolingual) lexicon and its transla-
tions to a particular language, ...
(Ciaramita and Johnson, 2004) is a multi-class av-
eraged perceptron classifier using syntactic and
narrow context features, with one component
trained on the data provided by Senseval and other...
... estimation, and successfully used it
for probabilistic context-free grammar domain adap-
tation (Roark and Bacchiani, 2003) and language
model adaptation (Bacchiani and Roark, 2003).
Count-merging can ... distributions and predominant sense ac-
quisition. In Proc. of Joint HLT-EMNLP05.
Y. K. Lee and H. T. Ng. 2002. Anempirical evaluation of
knowledge sources and learning algorithms for word
sense disambiguation. ... ICASSP03.
Y. S. Chan and H. T. Ng. 2005. Wordsense disambigua-
tion with distribution estimation. In Proc. of IJCAI05.
J. Chen, A. Schein, L. Ungar, and M. Palmer. 2006.
An empiricalstudy of the...
... the target
word, and sends these words (and the target) on to
the next module for disambiguation. Note that these
words must all be known to WordNet, and should
not include any stop–words.
However, ... Banerjee and T. Pedersen. 2002. An adapted Lesk
algorithm forwordsensedisambiguation using Word-
Net. In Proceedings of the Third International Confer-
ence on Intelligent Text Processing and ... (Patwardhan et al., 2003) and
(Banerjee and Pedersen, 2003) proposed that mea-
suring gloss overalps is just one way of determin-
ing semantic relatedness, and that wordsense dis-
ambiguation can...
... each sense
of one of the words. Pick one of the words,
say W2, and using WordNet, form a similarity
list for each sense of that word. For this, use
the words from the synset of each senseand ... For appli-
cations such as machine translation, fine grain
disambiguation works well but for information
extraction and some other applications this is
an overkill, and some senses may be lumped ... to-
gether. The ranking of senses is useful for many
applications.
References
E. Agirre and G. Rigau. 1995. A proposal for
word sensedisambiguation using conceptual
distance. In
Proceedings...
... of any significant results
for the orthogonality diagrams o+ and o- implies that
increased orthogonality cannot be used as an explanation
for this surprising result.
1.8.2 Edge variation
The control ... experiment,
and to the Australian Research Council, which funded
this research. Ethical clearance for this study was granted
by The University of Queensland, 2001.
References
COLEMAN, M. and STOTT ... this
experiment. Any formal empiricalstudy has limitations:
in our case, we were using university students as subjects,
rather than software engineers, and the comprehension
task and application were constrained...
... Precision and recall for the SENSELEARNER
semantic models, measured on the SENSEVAL-2 and
SENSEVAL-3 English all words data. Results for com-
binations of contextual (model*1/2) and collocational
(model*Coll) ... Interactive Poster and Demonstration Sessions,
pages 53–56, Ann Arbor, June 2005.
c
2005 Association for Computational Linguistics
SenseLearner: WordSenseDisambiguation
for All Words in Unrestricted ... Penn Treebank corpus annotated with WordNet
senses. The SENSEVAL-2 corpus includes a total of
2,473 annotated content words, and the SENSEVAL-
3 corpus includes annotations foran additional set
of...
... Daelemans and
Miles Osborne, editors, Proceedings of CoNLL-
2003, pages 184–187, Edmonton, Canada, 2003.
Raymond J. Mooney. Comparative experiments on
disambiguating word senses: An illustration ... adverbs and verbs.
For each word, training and test instances tagged
with WordNet senses are provided. There are an av-
erage of 7.8 senses per target word type. On average
109 training instances ... SIGLEX/SENSEVAL
Workshop onWordSense Disambiguation: Re-
cent Successes and Future Directions, pages 88–
94, Philadelphia, July 2002. SIGLEX, Associa-
tion for Computational Linguistics.
Konstantinos...
... Erlbanm Associates, Hillsdale, NJ.
van Rijsbergen, C. (1979) Information Retrieval, Second Editional,
Butterworths, London.
Veronis, Jean and Nancy Ide (1990), " ;Word SenseDisambiguation ... reported on two new word- sense
disambiguation systems, one trained on bilingual
material (the Canadian Hansards) and the other trained
on monolingual material (Roget's Thesaurus and
Grolier's ... P., R. Ilson, J. Ayto, et al. (1978),
Longman Dictionary of
Contemporary English,
Longman, Harlow and London.
Salton, G. (1989)
Automatic Text Processing,
Addison-Wesley.
Shipstone, E. (1960)...