Sciweavers

1053 search results - page 36 / 211
» Learning Rules to Improve a Machine Translation System
Sort
View
NLPRS
2001
Springer
15 years 4 months ago
Named Entity Recognition using Machine Learning Methods and Pattern-Selection Rules
Named Entity recognition, as a task of providing important semantic information, is a critical first step in Information Extraction and QuestionAnswering system. This paper propos...
Choong-Nyoung Seon, Youngjoong Ko, Jeong-Seok Kim,...
ICML
2010
IEEE
15 years 25 days ago
Rectified Linear Units Improve Restricted Boltzmann Machines
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all ...
Vinod Nair, Geoffrey E. Hinton
LREC
2008
125views Education» more  LREC 2008»
15 years 1 months ago
Adaptation of Relation Extraction Rules to New Domains
This paper presents various strategies for improving the extraction performance of less prominent relations with the help of the rules learned for similar relations, for which lar...
Feiyu Xu, Hans Uszkoreit, Hong Li, Niko Felger
SIGIR
2005
ACM
15 years 5 months ago
Iterative translation disambiguation for cross-language information retrieval
Finding a proper distribution of translation probabilities is one of the most important factors impacting the effectiveness of a crosslanguage information retrieval system. In th...
Christof Monz, Bonnie J. Dorr
ACL
2003
15 years 1 months ago
Text Chunking by Combining Hand-Crafted Rules and Memory-Based Learning
This paper proposes a hybrid of handcrafted rules and a machine learning method for chunking Korean. In the partially free word-order languages such as Korean and Japanese, a smal...
Seong-Bae Park, Byoung-Tak Zhang