Sciweavers

1487 search results - page 103 / 298
» Two Kinds of Metonymy
Sort
View
ACL
2006
13 years 10 months ago
Japanese Dependency Parsing Using Co-Occurrence Information and a Combination of Case Elements
In this paper, we present a method that improves Japanese dependency parsing by using large-scale statistical information. It takes into account two kinds of information not consi...
Takeshi Abekawa, Manabu Okumura
DLOG
2004
13 years 10 months ago
Using Non-Primitive Concept Definitions for Improving DL-based Knowledge Bases
Medical Terminological Knowledge Bases contain a large number of primitive concept definitions. This is due to the large number of natural kinds that are represented, and due to t...
Ronald Cornet, Ameen Abu-Hanna
DBSEC
2006
122views Database» more  DBSEC 2006»
13 years 10 months ago
Term Rewriting for Access Control
We demonstrate how access control models and policies can be represented by using term rewriting systems, and how rewriting may be used for evaluating access requests and for provi...
Steve Barker, Maribel Fernández
EMNLP
2006
13 years 10 months ago
Competitive generative models with structure learning for NLP classification tasks
In this paper we show that generative models are competitive with and sometimes superior to discriminative models, when both kinds of models are allowed to learn structures that a...
Kristina Toutanova
EMNLP
2006
13 years 10 months ago
Graph-based Word Clustering using a Web Search Engine
Word clustering is important for automatic thesaurus construction, text classification, and word sense disambiguation. Recently, several studies have reported using the web as a c...
Yutaka Matsuo, Takeshi Sakaki, Koki Uchiyama, Mits...