Sciweavers

2206 search results - page 240 / 442
» Using Classification to Generate Text
Sort
View
IJDMB
2008
128views more  IJDMB 2008»
15 years 1 months ago
Protein homology detection with biologically inspired features and interpretable statistical models
: Computational classification of proteins using methods such as string kernels and Fisher-SVM has demonstrated great success. However, the resulting models do not offer an immedia...
Pai-Hsi Huang, Vladimir Pavlovic
MT
2002
118views more  MT 2002»
15 years 1 months ago
Principles of Context-Based Machine Translation Evaluation
This article defines a Framework for Machine Translation Evaluation (FEMTI) which relates the quality model used to evaluate a machine translation system to the purpose and context...
Eduard H. Hovy, Margaret King, Andrei Popescu-Beli...
AAAI
2012
13 years 4 months ago
Ontological Smoothing for Relation Extraction with Minimal Supervision
Relation extraction, the process of converting natural language text into structured knowledge, is increasingly important. Most successful techniques use supervised machine learni...
Congle Zhang, Raphael Hoffmann, Daniel S. Weld
AI
2005
Springer
15 years 1 months ago
Choosing words in computer-generated weather forecasts
One of the main challenges in automatically generating textual weather forecasts is choosing appropriate English words to communicate numeric weather data. A corpus-based analysis...
Ehud Reiter, Somayajulu Sripada, Jim Hunter, Jin Y...
ICML
2002
IEEE
16 years 2 months ago
Syllables and other String Kernel Extensions
During the last years, the use of string kernels that compare documents has been shown to achieve good results on text classification problems. In this paper we introduce the appl...
Craig Saunders, Hauke Tschach, John Shawe-Taylor