Sciweavers

16 search results - page 2 / 4
» Grammar Extraction from Treebanks for Hindi and Telugu
Sort
View
IJCNLP
2004
Springer
13 years 10 months ago
The Hinoki Treebank A Treebank for Text Understanding
In this paper we describe the motivation for and construction of a new Japanese lexical resource: the Hinoki treebank. The treebank is built from dictionary definition sentences, ...
Francis Bond, Sanae Fujita, Chikara Hashimoto, Kan...
LRE
2008
100views more  LRE 2008»
13 years 5 months ago
LTAG-spinal and the Treebank
Abstract. We introduce LTAG-spinal, a novel variant of traditional Lexicalized Tree Adjoining Grammar (LTAG) with desirable linguistic, computational and statistical properties. Un...
Libin Shen, Lucas Champollion, Aravind K. Joshi
ACL
2000
13 years 6 months ago
Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar
We discuss the advantages of lexicalized tree-adjoining grammar as an alternative to lexicalized PCFG for statistical parsing, describingthe induction of a probabilistic LTAG mode...
David Chiang
CSL
2007
Springer
13 years 5 months ago
Modeling durations of syllables using neural networks
In this paper, we propose a neural network model for predicting the durations of syllables. A four layer feedforward neural network trained with backpropagation algorithm is used ...
K. Sreenivasa Rao, B. Yegnanarayana
INFORMATICALT
2008
122views more  INFORMATICALT 2008»
13 years 4 months ago
Modeling Phone Duration of Lithuanian by Classification and Regression Trees, using Very Large Speech Corpus
Classification and regression tree approach was used in this research to model phone duration of Lithuanian. 300 thousand samples of vowels and 400 thousand samples of consonants e...
Giedrius Norkevicius, Gailius Raskinis