AAAISep, 2018

神经实体推理器在 NER 中实现全局一致性

TL;DRNeural Entity Reasoner (NE-Reasoner) framework uses symbolic memory and specific interaction-pooling mechanism to introduce global consistency of recognized entities into Neural Reasoner over Named Entity Recognition (NER) task, and can accommodate ambiguous words and rare name entities to outperform conventional NER models in most cases on both English and Chinese NER datasets.