Sciweavers

373 search results - page 60 / 75
» Trainable Methods for Surface Natural Language Generation
Sort
View
TLDI
2003
ACM
135views Formal Methods» more  TLDI 2003»
15 years 2 months ago
Typed compilation of recursive datatypes
Standard ML employs an opaque (or generative) semantics of datatypes, in which every datatype declaration produces a new type that is different from any other type, including othe...
Joseph Vanderwaart, Derek Dreyer, Leaf Petersen, K...
ALT
2006
Springer
15 years 6 months ago
Probabilistic Generalization of Simple Grammars and Its Application to Reinforcement Learning
Abstract. Recently, some non-regular subclasses of context-free grammars have been found to be efficiently learnable from positive data. In order to use these efficient algorithms ...
Takeshi Shibata, Ryo Yoshinaka, Takashi Chikayama
NLP
2000
15 years 1 months ago
Monte-Carlo Sampling for NP-Hard Maximization Problems in the Framework of Weighted Parsing
Abstract. The purpose of this paper is (1) to provide a theoretical justification for the use of Monte-Carlo sampling for approximate resolution of NP-hard maximization problems in...
Jean-Cédric Chappelier, Martin Rajman
LREC
2008
117views Education» more  LREC 2008»
14 years 11 months ago
Evolutionary Basic Notions for a Thematic Representation of General Knowledge
In the field of Natural Language Processing, in order to work out a thematic representation system of general knowledge, methods relying on thesaurus have been used for about twen...
Alain Joubert, Mathieu Lafourcade
VISUALIZATION
1991
IEEE
15 years 1 months ago
A Scientific Visualization Synthesizer
or vectors at every mesh point may lead to a very cluttered image. Continuous coloring or data mapping, on the other hand, provide a smooth representation of the data. The use of t...
Roger Crawfis, M. J. Allison