Simplify the Usage of Lexicon in Chinese NER

08/16/2019
by   Minlong Peng, et al.
0

Recently, many works have tried to utilizing word lexicon to augment the performance of Chinese named entity recognition (NER). As a representative work in this line, Lattice-LSTM zhang2018chinese has achieved new state-of-the-art performance on several benchmark Chinese NER datasets. However, Lattice-LSTM suffers from a complicated model architecture, resulting in low computational efficiency. This will heavily limit its application in many industrial areas, which require real-time NER response. In this work, we ask the question: if we can simplify the usage of lexicon and, at the same time, achieve comparative performance with Lattice-LSTM for Chinese NER? Started with this question and motivated by the idea of Lattice-LSTM, we propose a concise but effective method to incorporate the lexicon information into the vector representations of characters. This way, our method can avoid introducing a complicated sequence modeling architecture to model the lexicon information. Instead, it only needs to subtly adjust the character representation layer of the neural sequence model. Experimental study on four benchmark Chinese NER datasets shows that our method can achieve much faster inference speed, comparative or better performance over Lattice-LSTM and its follwees. It also shows that our method can be easily transferred across difference neural architectures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/05/2018

Chinese NER Using Lattice LSTM

We investigate a lattice-structured LSTM model for Chinese NER, which en...
research
04/24/2020

FLAT: Chinese NER Using Flat-Lattice Transformer

Recently, the character-word lattice structure has been proved to be eff...
research
01/15/2020

FGN: Fusion Glyph Network for Chinese Named Entity Recognition

Chinese NER is a challenging task. As pictographs, Chinese characters co...
research
11/07/2019

Porous Lattice-based Transformer Encoder for Chinese NER

Incorporating lattices into character-level Chinese named entity recogni...
research
05/12/2022

NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition

Recently, Flat-LAttice Transformer (FLAT) has achieved great success in ...
research
01/16/2018

Adversarial Learning for Chinese NER from Crowd Annotations

To quickly obtain new labeled data, we can choose crowdsourcing as an al...
research
10/30/2018

Subword Encoding in Lattice LSTM for Chinese Word Segmentation

We investigate a lattice LSTM network for Chinese word segmentation (CWS...

Please sign up or login with your details

Forgot password? Click here to reset