Coreference-aware representation learning for neural named entity recognition
US11354506B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 30, 2019 |
| Grant date | Jun 7, 2022 |
| Priority date | — |
| Expiry date | Sep 7, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Previous neural network models that perform named entity recognition (NER) typically treat the input sentences as a linear sequence of words but ignore rich structural information, such as the coreference relations among non-adjacent words, phrases, or entities. Presented herein are novel approaches to learn coreference-aware word representations for the NER task. In one or more embodiments, a “CNN-BiLSTM-CRF” neural architecture is modified to include a coreference layer component on top of the BiLSTM layer to incorporate coreferential relations. Also, in one or more embodiments, a coreference regularization is added during training to ensure that the coreferential entities share similar representations and consistent predictions within the same coreference cluster. A model embodiment achieved new state-of-the-art performance when tested.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.