MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition

07/12/2021
by   Shuang Wu, et al.
0

Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the information of the Chinese character structure after integrating the lexical information. Chinese characters have evolved from pictographs since ancient times, and their structure often reflects more information about the characters. This paper presents a novel Multi-metadata Embedding based Cross-Transformer (MECT) to improve the performance of Chinese NER by fusing the structural information of Chinese characters. Specifically, we use multi-metadata embedding in a two-stream Transformer to integrate Chinese character features with the radical-level embedding. With the structural characteristics of Chinese characters, MECT can better capture the semantic information of Chinese characters for NER. The experimental results obtained on several well-known benchmarking datasets demonstrate the merits and superiority of the proposed MECT method.[The source code of the proposed method is publicly available at https://github.com/CoderMusou/MECT4CNER.]

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/16/2021

MFE-NER: Multi-feature Fusion Embedding for Chinese Named Entity Recognition

Pre-trained language models lead Named Entity Recognition (NER) into a n...
research
08/28/2019

Exploiting Multiple Embeddings for Chinese Named Entity Recognition

Identifying the named entities mentioned in text would enrich many seman...
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
11/07/2019

Porous Lattice-based Transformer Encoder for Chinese NER

Incorporating lattices into character-level Chinese named entity recogni...
research
07/16/2020

SLK-NER: Exploiting Second-order Lexicon Knowledge for Chinese NER

Although character-based models using lexicon have achieved promising re...
research
03/09/2023

Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction

Recently, many studies incorporate external knowledge into character-lev...
research
04/08/2015

Exploring Lexical, Syntactic, and Semantic Features for Chinese Textual Entailment in NTCIR RITE Evaluation Tasks

We computed linguistic information at the lexical, syntactic, and semant...

Please sign up or login with your details

Forgot password? Click here to reset