Sciweavers

501 search results - page 72 / 101
» Improving Language Models by Clustering Training Sentences
Sort
View
IVA
2010
Springer
13 years 7 months ago
Interactive Motion Modeling and Parameterization by Direct Demonstration
Abstract. While interactive virtual humans are becoming widely used in education, training and therapeutic applications, building animations which are both realistic and parameteri...
Carlo Camporesi, Yazhou Huang, Marcelo Kallmann
ICASSP
2011
IEEE
13 years 27 days ago
Concept-based classification for multi-document summarization
Documents often contain inherently many concepts reflecting specific and generic aspects. To automatically generate a short summary text of documents on similar topics, it is im...
Asli Çelikyilmaz, Dilek Hakkani-Tür
SIGIR
2006
ACM
14 years 3 months ago
User modeling for full-text federated search in peer-to-peer networks
User modeling for information retrieval has mostly been studied to improve the effectiveness of information access in centralized repositories. In this paper we explore user model...
Jie Lu, James P. Callan
NLPRS
2001
Springer
14 years 1 months ago
A Maximum Entropy Tagger with Unsupervised Hidden Markov Models
We describe a new tagging model where the states of a hidden Markov model (HMM) estimated by unsupervised learning are incorporated as the features in a maximum entropy model. Our...
Jun'ichi Kazama, Yusuke Miyao, Jun-ichi Tsujii
ACL
2012
11 years 11 months ago
Arabic Retrieval Revisited: Morphological Hole Filling
Due to Arabic’s morphological complexity, Arabic retrieval benefits greatly from morphological analysis – particularly stemming. However, the best known stemming does not hand...
Kareem Darwish, Ahmed Ali