Nannan Su
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Nannan Su has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Dantong Ouyang
College of Computer Science and Technology, Jilin University, Changchun 130012, China
1 shared publication - Jiamian Xing
College of Cybersecurity, Changchun University, Changchun 130022, China
1 shared publication - Jing Bian
College of Computer Science and Technology, Changchun University, Changchun 130022, China
1 shared publication - Ping Feng
College of Computer Science and Technology, Changchun University, Changchun, China
1 shared publication
Latest Publications
- Open Access
- 26 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (3) , 1058
A Study of Entity Relationship Extraction Algorithms Based on Symmetric Interaction between Data, Models, and Inference Algorithms
The purpose of this paper is to address the extraction of entities and relationships from unstructured Chinese text, with a particular emphasis on the challenges of Named Entity Recognition (NER) and Relation Extraction (RE). This will be achieved by integrating external lexical information and utilizing the abundant semantic information available in Chinese. We utilize a pipeline model that is applied separately to NER and RE by introducing an innovative NER model that integrates Chinese pinyin, characters, and words to enhance recognition capabilities. Simultaneously, we incorporate information such as entity distance, sentence length, and part-of-speech to improve the performance of relation extraction. We also delve into the interactions among data, models, and inference algorithms to improve learning efficiency in addressing this challenge. In comparison to existing methods, our model has achieved significant results.
- 26 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (3) , 1058
Open AccessA Study of Entity Relationship Extraction Algorithms Based on Symmetric Interaction between Data, Models, and Inference Algorithms
The purpose of this paper is to address the extraction of entities and relationships from unstructured Chinese text, with a particular emphasis on the challenges of Named Entity Recognition (NER) and Relation Extraction (RE). This will be achieved by integrating external lexical information and utilizing the abundant semantic information available in Chinese. We utilize a pipeline model that is applied separately to NER and RE by introducing an innovative NER model that integrates Chinese pinyin, characters, and words to enhance recognition capabilities. Simultaneously, we incorporate information such as entity distance, sentence length, and part-of-speech to improve the performance of relation extraction. We also delve into the interactions among data, models, and inference algorithms to improve learning efficiency in addressing this challenge. In comparison to existing methods, our model has achieved significant results.