KBERT
论文:《K-BERT: Enabling Language Representation with Knowledge Graph》
论文地址:https://arxiv.org/pdf/1909.07606v1
git地址:https://github.com/autoliuweijie/K-BERT
SoftLexicon
出自ACL 2020的Simplify the Usage of Lexicon in Chinese NER
git:https://github.com/v-mipeng/LexiconAugmentedNER
论文:https://arxiv.org/abs/1908.05969
FLAT
Chinese NER Using Flat-Lattice Transformer
论文:https://arxiv.org/pdf/2004.11795.pdf
git:https://github.com/LeeSureman/Flat-Lattice-Transformer
lattice = char + lexion bigram
raw_emb = ( lattice_emb + bigram_emb +bert_emb )
pos_emb = (pos_s, pos_e)
emb = f(raw_emb, pos_emb)
emb + transformer一层 + crf = seqlabel
备注:bert使用的是lattice词表
A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding
论文:https://arxiv.org/pdf/1909.02188.pdf
git:
DCA-NET
A Co-Interactive Transformer for Joint Slot Filling and Intent Detection