luoyu1022 / lattice_lstm_tf

Lattice LSTM -- TensorFlow

This is an experimental Tensorflow implementation of Lattice LSTM - Chinese NER Using Lattice LSTM. For details about Lattice LSTM please refer to the paper Chinese NER Using Lattice LSTM by Yue Zhang and Jie Yang.

Requirement:

Python: 3.5
TensorFlow: 1.5

Input format:

CoNLL format (prefer BIOES tag scheme), with each character its label for one line. Sentences are splited with a null line.

美	B-LOC
国	E-LOC
的	O
华	B-PER
莱	I-PER
士	E-PER

我	O
跟	O
他	O
谈	O
笑	O
风	O
生	O 

Pretrained Embeddings:

The pretrained character and word embeddings are the same with the embeddings in the baseline of RichWordSegmentor

Character embeddings: gigaword_chn.all.a2b.uni.ite50.vec

Word(Lattice) embeddings: ctb.50d.vec

How to run the code?

Resume NER data

Crawled from the Sina Finance, it includes the resumes of senior executives from listed companies in the Chinese stock market. Details can be found in our paper.

lattice_lstm_tf's Issues

Hello, why is there no code in lattice_lstm_tf's project?

If you have, can you share it? please