Chinese NER Using Lattice LSTM

ACL 2018 Yue ZhangJie Yang

We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word and word sequence information... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Chinese Named Entity Recognition MSRA Lattice F1 93.18 # 2
Chinese Named Entity Recognition OntoNotes 4 Lattice F1 73.88 # 1
Chinese Named Entity Recognition Resume NER Lattice F1 94.46 # 2
Chinese Named Entity Recognition Weibo NER Lattice F1 58.79 # 1