Robust Chinese Named Entity Recognition Based on Fusion Graph Embedding
Open Access
- 22 January 2023
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 12 (3) , 569
Abstract
Named entity recognition is an important basic task in the field of natural language processing. The current mainstream named entity recognition methods are mainly based on the deep neural network model. The vulnerability of the deep neural network itself leads to a significant decline in the accuracy of named entity recognition when there is adversarial text in the text. In order to improve the robustness of named entity recognition under adversarial conditions, this paper proposes a Chinese named entity recognition model based on fusion graph embedding. Firstly, the model encodes and represents the phonetic and glyph information of the input text through graph learning and integrates above-multimodal knowledge into the model, thus enhancing the robustness of the model. Secondly, we use the Bi-LSTM to further obtain the context information of the text. Finally, conditional random field is used to decode and label entities. The experimental results on OntoNotes4.0, MSRA, Weibo, and Resume datasets show that the F1 values of this model increased by 3.76%, 3.93%, 4.16%, and 6.49%, respectively, in the presence of adversarial text, which verifies the effectiveness of this model.Keywords
Funding Information
- National Natural Science Foundation of China (62002384)
This publication has 15 references indexed in Scilit:
- Joint Character-Level Word Embedding and Adversarial Stability Training to Defend Adversarial TextProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Robust Encodings: A Framework for Combating Adversarial Typos2020
- Toward Mitigating Adversarial TextsInternational Journal of Computer Applications, 2019
- Context-Sensitive Malicious Spelling Error Correction2019
- Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network2019
- Robust Machine Comprehension Models via Adversarial Training2018
- Core techniques of question answering systems over knowledge bases: a surveyKnowledge and Information Systems, 2017
- node2vec2016
- Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings2015
- Convolutional Neural Networks for Sentence Classification2014