USTC-NELSLIP at SemEval-2022 Task 11: Gazetteer-Adapted Integration Network for Multilingual Complex Named Entity Recognition
This work addresses multilingual complex named entity recognition for NLP applications, representing an incremental improvement with a novel integration method.
The paper tackled multilingual complex named entity recognition by proposing a gazetteer-adapted integration network (GAIN), which improved performance and achieved 1st place on three tracks and 2nd on ten others in the SemEval-2022 task.
This paper describes the system developed by the USTC-NELSLIP team for SemEval-2022 Task 11 Multilingual Complex Named Entity Recognition (MultiCoNER). We propose a gazetteer-adapted integration network (GAIN) to improve the performance of language models for recognizing complex named entities. The method first adapts the representations of gazetteer networks to those of language models by minimizing the KL divergence between them. After adaptation, these two networks are then integrated for backend supervised named entity recognition (NER) training. The proposed method is applied to several state-of-the-art Transformer-based NER models with a gazetteer built from Wikidata, and shows great generalization ability across them. The final predictions are derived from an ensemble of these trained models. Experimental results and detailed analysis verify the effectiveness of the proposed method. The official results show that our system ranked 1st on three tracks (Chinese, Code-mixed and Bangla) and 2nd on the other ten tracks in this task.