Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Frequently asked questions and document retrieval using bidirectional encoder representations from transformers (BERT) model trained on generated paraphrases

Frequently asked questions and document retrieval using bidirectional encoder representations from transformers (BERT) model trained on generated paraphrases

US Patent 11775839 · Granted Oct 3, 2023

Estimated economic value: $6,984,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Techniques for automatic filling of an input form to generate a listing2025
Identifying a semantic representation for texts by expanding the embedding space2025
Ranking of messages in dialogs using fixed point operations2024
Ranking of messages in dialogs using fixed point operations2024
Removing unnecessary history from reinforcement learning state2024
Method and system for table retrieval using multimodal deep co-learning with hel2024
Clarification questions selection for conversational search, trained from human-2023
Clarification questions selection for conversational search, trained from human-2023
Dataset balancing via quality-controlled sample generation2023
Dynamically generating facets using graph partitioning2023
Dynamically generating facets using graph partitioning2023
Dynamically generating facets using graph partitioning2023