Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Natural language generation through character-based recurrent neural networks with finite-state prior knowledge

Natural language generation through character-based recurrent neural networks with finite-state prior knowledge

US Patent 10049106 · Granted Aug 14, 2018

Estimated economic value: $2,705,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Sampling from discrete energy-based models with quality/efficiency trade-off2025
Method and system for controlling distributions of attributes in language models2024
Methods and systems for producing neural sequential models2024
Method and system for training neural sequence-to-sequence models by incorporati2023
Symbolic priors for recurrent neural network based semantic parsing2020
Dialog device with dialog support generated using a mixture of language models c2019
Methods and systems for transmitting prioritized messages to employees2018
Semantic parsing using deep neural networks for predicting canonical forms2018
Sequence-based structured prediction for semantic parsing2017
Joint algorithm for sampling and optimization and natural language processing ap2017
Method and system for assisting contact center agents in composing electronic ma2017
Dynamic bi-phrases for statistical machine translation2017