SFE-AI at SemEval-2022 Task 11: Low-Resource Named Entity Recognition using Large Pre-trained Language Models
This work addresses the problem of improving NER performance in low-resource languages for NLP researchers, but it is incremental as it builds on existing ensemble techniques.
The paper tackled low-resource named entity recognition by proposing an adaptive ensemble method using a Transformer layer to weight different pre-trained language models, achieving superior F1 scores of 0.85 in Farsi and 0.83 in Dutch on the MultiCoNER dataset.
Large scale pre-training models have been widely used in named entity recognition (NER) tasks. However, model ensemble through parameter averaging or voting can not give full play to the differentiation advantages of different models, especially in the open domain. This paper describes our NER system in the SemEval 2022 task11: MultiCoNER. We proposed an effective system to adaptively ensemble pre-trained language models by a Transformer layer. By assigning different weights to each model for different inputs, we adopted the Transformer layer to integrate the advantages of diverse models effectively. Experimental results show that our method achieves superior performances in Farsi and Dutch.