Sciweavers

1343 search results - page 41 / 269
» Learning to Complete Sentences
Sort
View
CIMCA
2006
IEEE
15 years 2 months ago
Identification of Document Language is Not yet a Completely Solved Problem
Existing Language Identification (LID) approaches do reach 100% precision, in most common situations, when dealing with documents written in just one language, and when those docu...
Joaquim Ferreira da Silva, Gabriel Pereira Lopes
SIGKDD
2010
151views more  SIGKDD 2010»
14 years 7 months ago
Limitations of matrix completion via trace norm minimization
In recent years, compressive sensing attracts intensive attentions in the field of statistics, automatic control, data mining and machine learning. It assumes the sparsity of the ...
Xiaoxiao Shi, Philip S. Yu
ICML
2010
IEEE
15 years 2 months ago
Label Ranking under Ambiguous Supervision for Learning Semantic Correspondences
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supe...
Antoine Bordes, Nicolas Usunier, Jason Weston
NLPRS
2001
Springer
15 years 5 months ago
A New Prosodic Phrasing Model for Chinese TTS Systems
This paper proposes a new prosodic phrasing model for Chinese text-tospeech systems. First, in contrast to the commonly used CART techniques, we propose a new inductive learning a...
Weijun Chen, Fuzong Lin, Jianmin Li, Bo Zhang
CANDC
2004
ACM
15 years 25 days ago
Retrieving definitional content for ontology development
Ontology construction requires an understanding of the meaning and usage of its encoded concepts. While definitions found in dictionaries or glossaries may be adequate for many co...
Lawrence H. Smith, W. John Wilbur