Sciweavers

349 search results - page 54 / 70
» Training a Natural Language Generator From Unaligned Data
Sort
View
TSD
2004
Springer
15 years 4 months ago
Modeling Prosodic Structures in Linguistically Enriched Environments
A significant challenge in Text-to-Speech (TtS) synthesis is the formulation of the prosodic structures (phrase breaks, pitch accents, phrase accents and boundary tones) of uttera...
Gerasimos Xydas, Dimitris Spiliotopoulos, Georgios...
SIGIR
2005
ACM
15 years 4 months ago
Web-based acquisition of Japanese katakana variants
This paper describes a method of detecting Japanese Katakana variants from a large corpus. Katakana words, which are mainly used as loanwords, cause problems with information retr...
Takeshi Masuyama, Hiroshi Nakagawa
JAIR
2008
164views more  JAIR 2008»
14 years 11 months ago
Gesture Salience as a Hidden Variable for Coreference Resolution and Keyframe Extraction
Gesture is a non-verbal modality that can contribute crucial information to the understanding of natural language. But not all gestures are informative, and non-communicative hand...
Jacob Eisenstein, Regina Barzilay, Randall Davis
CVPR
2001
IEEE
16 years 1 months ago
Clustering Art
We extend a recently developed method [1] for learning the semantics of image databases using text and pictures. We incorporate statistical natural language processing in order to...
Kobus Barnard, Pinar Duygulu, David A. Forsyth
WSDM
2012
ACM
309views Data Mining» more  WSDM 2012»
13 years 6 months ago
Mining contrastive opinions on political texts using cross-perspective topic model
This paper presents a novel opinion mining research problem, which is called Contrastive Opinion Modeling (COM). Given any query topic and a set of text collections from multiple ...
Yi Fang, Luo Si, Naveen Somasundaram, Zhengtao Yu