Dipanjan Das
19Patents
5h-index
35Co-inventors
62Inventor score
Filing activity: Oct 8, 2010 → Sep 25, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US9536522B1 | Training a natural language processing model with information retrieval model annotations | Physics | 70 | Active |
| US8560477B1 | Graph-based semi-supervised learning of structured tagging models | Physics | 19 | Active |
| US9262406B1 | Semantic frame identification with distributed word representations | Physics | 17 | Active |
| US9311299B1 | Weakly supervised part-of-speech tagging with coupled token and type constraints | Physics | 14 | Active |
| US11423068B2 | Canonicalizing search queries to natural language questions | Physics | 8 | Active |
| US11551002B2 | Learned evaluation model for grading quality of natural language generation outputs | Physics | 4 | Active |
| US11704506B2 | Learned evaluation model for grading quality of natural language generation outputs | Physics | 3 | Active |
| US9779087B2 | Cross-lingual discriminative learning of sequence models with posterior regularization | Physics | 3 | Active |
| US11551394B2 | Audio-speech driven animated talking face generation using a cascaded generative adversarial network | Physics | 2 | Active |
| US10289952B2 | Semantic frame identification with distributed word representations | Physics | 2 | Active |
| US12013885B2 | Canonicalizing search queries to natural language questions | Physics | 1 | Active |
| US11670047B2 | System and method for integrating objects in monocular slam | Physics | 1 | Active |
| US11295501B1 | Method and system for generating face animations from speech signal input | Physics | 1 | Active |
| US12282878B2 | Method and system for identifying actions to improve customer experience | Physics | 0 | Active |
| US12223273B2 | Learned evaluation model for grading quality of natural language generation outputs | Physics | 0 | Active |
| US11597080B2 | Knowledge partitioning for task execution by conversational tele-presence robots in a geographically separated environment | Physics | 0 | Active |
| US11875115B2 | Learned evaluation model for grading quality of natural language generation outputs | Physics | 0 | Active |
| US12073189B2 | Learned evaluation model for grading quality of natural language generation outputs | Physics | 0 | Active |
| US11887238B2 | Method and system for generating 2D animated lip images synchronizing to an audio signal | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.