Systems and methods for end-to-end deep reinforcement learning based coreference resolution
US11630953B2 · kind B2 · utility
1Cited by
6References
21Claims
0Family size
Assignees
Inventors
Key dates
| Filing date | Jul 25, 2019 |
| Grant date | Apr 18, 2023 |
| Priority date | — |
| Expiry date | Aug 6, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/092
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Described herein are embodiments for end-to-end reinforcement learning based coreference resolution models to directly optimize coreference evaluation metrics. Embodiments of a reinforced policy gradient model are disclosed to incorporate reward associated with a sequence of coreference linking actions. Furthermore, maximum entropy regularization may be used for adequate exploration to prevent a model embodiment from prematurely converging to a bad local optimum. Experiments on datasets compared with state-of-the-art methods verified the effectiveness of embodiments.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.