USTC-NELSLIP 在 SemEval-2022 任务 11：面向多语言复杂命名实体识别的词典自适应集成网络
USTC-NELSLIP at SemEval-2022 Task 11: Gazetteer-Adapted Integration Network for Multilingual Complex Named Entity Recognition
AI总结：
针对多语言复杂命名实体识别任务，提出词典自适应集成网络（GAIN），通过KL散度适配词典与语言模型表示并集成训练，在SemEval-2022 MultiCoNER中取得3项第一、10项第二的优异成绩。
摘要：
本文描述了 USTC-NELSLIP 团队为 SemEval-2022 任务 11 多语言复杂命名实体识别（MultiCoNER）所开发的系统。我们提出了一种词典自适应集成网络（GAIN），以提高语言模型在识别复杂命名实体时的性能。该方法首先通过最小化词典网络与语言模型表示之间的 KL 散度，使词典网络的表示适应语言模型的表示。适应后，这两个网络被集成用于后端监督命名实体识别（NER）训练。所提出的方法应用于多个基于 Transformer 的最先进的 NER 模型，并使用从 Wikidata 构建的词典，展示了跨这些模型的强大泛化能力。最终预测来自这些训练模型的集成。实验结果和详细分析验证了所提出方法的有效性。官方结果显示，我们的系统在三个赛道（中文、代码混合和孟加拉语）中排名第一，并在该任务的其他十个赛道中排名第二。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
