Sciweavers

431 search results - page 6 / 87
» A Fully Statistical Approach to Natural Language Interfaces
Sort
View
ACL
2007
14 years 11 months ago
A fully Bayesian approach to unsupervised part-of-speech tagging
Unsupervised learning of linguistic structure is a difficult problem. A common approach is to define a generative model and maximize the probability of the hidden structure give...
Sharon Goldwater, Tom Griffiths
LKR
2008
14 years 11 months ago
Design and Prototype of a Large-Scale and Fully Sense-Tagged Corpus
Sense tagged corpus plays a very crucial role to Natural Language Processing, especially on the research of word sense disambiguation and natural language understanding. Having a l...
Sue-jin Ker, Chu-Ren Huang, Jia-Fei Hong, Shi-Yin ...
ICPR
2000
IEEE
15 years 1 months ago
A New Approach to Speech-Input Statistical Translation
The statistical pattern recognition is a promising framework for text-to-text translation. However, a natural extension to speech-input translation is not straightforward. In this...
Ismael García-Varea, Alberto Sanchís...
AI
2009
Springer
15 years 1 months ago
Executable Specifications of Fully General Attribute Grammars with Ambiguity and Left-Recursion
Abstract. A top-down parsing algorithm has been constructed to accommodate any form of ambiguous context-free grammar, augmented with semantic rules with arbitrary attribute depend...
Rahmatullah Hafiz
CICLING
2004
Springer
15 years 2 months ago
Towards Programming in Everyday Language: A Case for Email Management
Abstract. In order to extend the application domain of natural language interfaces to more realistic tasks without the decrease of user’s performance, it is desirable for users t...
Toru Sugimoto, Noriko Ito, Shino Iwashita, Michio ...