Sciweavers

142 search results - page 19 / 29
» Disambiguating Highly Ambiguous Words
Sort
View
LREC
2008
146views Education» more  LREC 2008»
13 years 9 months ago
A Contextual Dynamic Network Model for WSD Using Associative Concept Dictionary
Many of the Japanese ideographs (Chinese characters) have a few meanings. Such ambiguities should be identified by using their contextual information. For example, we have an ideo...
Jun Okamoto, Kiyoko Uchiyama, Shun Ishizaki
ACL
2003
13 years 9 months ago
Syntactic Features and Word Similarity for Supervised Metonymy Resolution
We present a supervised machine learning algorithm for metonymy resolution, which exploits the similarity between examples of conventional metonymy. We show that syntactic head-mo...
Malvina Nissim, Katja Markert
ANLP
1992
116views more  ANLP 1992»
13 years 8 months ago
Automatic Learning for Semantic Collocation
The real di culty in development of practical NLP systems comes from the fact that we do not have e ective means for gathering \knowledge". In this paper, we propose an algor...
Satoshi Sekine, Jeremy J. Carroll, Sophia Ananiado...
CICLING
2007
Springer
14 years 1 months ago
Text Categorization for Improved Priors of Word Meaning
Distributions of the senses of words are often highly skewed. This fact is exploited by word sense disambiguation (WSD) systems which back off to the predominant (most frequent) s...
Rob Koeling, Diana McCarthy, John Carroll
IJCAI
2007
13 years 9 months ago
A Flexible Unsupervised PP-Attachment Method Using Semantic Information
In this paper we revisit the classical NLP problem of prepositional phrase attachment (PPattachment). Given the pattern V −NP1−P −NP2 in the text, where V is verb, NP1 is a ...
Srinivas Medimi, Pushpak Bhattacharyya