Patent №
US 6,178,396
Granted
2001-01-23
Filed 1997
Owner
FUJITSU LIMITED
Lab
—
AI components
4
ml · nlp · speech · kr
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
08828901
A token is attached to a word class sequence whose probability of appearance in text data is equal to or more than a predetermined value. A set of words and tokens included in a word/token sequence concerning the text data, is separated so that a probability of generation of the word/token sequence concerning the text data becomes the highest. The token is then replaced with a phrase included in the text data.
Machine learningNatural languageSpeechKnowledge representationG06F 40/216G06F 40/289G06F 40/55G10L 15/197
AI classification
Natural language1.00
Speech1.00
Machine learning1.00
Knowledge representation1.00
Vision0.05
AI hardware0.01
Evolutionary computation0.00
Planning0.00
Ownership
FUJITSU LIMITED
assignment · 84940313
Assignors
USHIODA, AKIRA
On an employer assignment, the assignors are typically the inventors.
From the same owner
OPTIMIZATION APPARATUS AND CONTROL METHOD THEREOFUS 12,694,267 · 2026QUANTUM CIRCUIT, QUANTUM COMPUTER, AND METHOD OF MANUFACTURING QUANTUM CIRCUITUS 12,694,318 · 2026GENERATION METHOD AND INFORMATION PROCESSING APPARATUSUS 12,694,718 · 2026INFERENCE METHOD AND INFORMATION PROCESSING APPARATUSUS 12,688,340 · 2026TRAINING METHOD, STORAGE MEDIUM, AND TRAINING DEVICEUS 12,688,412 · 2026RECORDING MEDIUM, MACHINE LEARNING METHOD, AND MACHINE LEARNING DEVICEUS 12,682,284 · 2026STORAGE MEDIUM AND INFORMATION PROCESSING DEVICEUS 12,682,333 · 2026COMPUTER-READABLE RECORDING MEDIUM STORING DESIGN ASSIST PROGRAM, DESIGN ASSIST METHOD, AND DESIGN ASSIST APPARATUSUS 12,682,474 · 2026