no code implementations • 20 Dec 2021 • Yong Cao, Yukun Feng, Shaohui Kuang, Gu Xu
In almost all text generation applications, word sequences are constructed in a left-to-right (L2R) or right-to-left (R2L) manner, as natural language sentences are written either L2R or R2L.
1 code implementation • IJCNLP 2019 • Changmeng Zheng, Yi Cai, Jingyun Xu, Ho-fung Leung, Gu Xu, ong
We propose a boundary-aware neural model for nested NER which leverages entity boundaries to predict entity categorical labels.
Ranked #11 on Named Entity Recognition (NER) on GENIA