DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition

	DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition
	Tan, Zeqi 1,2; Huang, Shen 1; Jia, Zixia1,3 ; Cai, Jiong1,3 ; Li, Yinghui 1,4; Lu, Weiming 2; Zhuang, Yueting 2; Tu, Kewei3 ; Xie, Pengjun 1; Huang, Fei 1; Jiang, Yong 1
	2023
会议录名称	17TH INTERNATIONAL WORKSHOP ON SEMANTIC EVALUATION, SEMEVAL-2023
摘要	The MultiCoNER II shared task aims to tackle multilingual named entity recognition (NER) in fine-grained and noisy scenarios, and it inherits the semantic ambiguity and low-context setting of the MultiCoNER I task. To cope with these problems, the previous top systems in the MultiCoNER I either incorporate the knowledge bases or gazetteers. However, they still suffer from insufficient knowledge, limited context length, single retrieval strategy. In this paper, our team DAMO-NLP proposes a unified retrieval-augmented system (U-RaNER) for fine-grained multilingual NER. We perform error analysis on the previous top systems and reveal that their performance bottleneck lies in insufficient knowledge. Also, we discover that the limited context length causes the retrieval knowledge to be invisible to the model. To enhance the retrieval context, we incorporate the entity-centric Wikidata knowledge base, while utilizing the infusion approach to broaden the contextual scope of the model. Also, we explore various search strategies and refine the quality of retrieval knowledge. Our system(1) wins 9 out of 13 tracks in the MultiCoNER II shared task. Additionally, we compared our system with ChatGPT, one of the large language models which have unlocked strong capabilities on many tasks. The results show that there is still much room for improvement for ChatGPT on the extraction task.
会议名称	17th International Workshop on Semantic Evaluation (SemEval)
出版地	209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA
会议地点	null,Toronto,CANADA
会议日期	JUL 13-14, 2023
URL	查看原文
收录类别	CPCI-S ; CPCI-SH
语种	英语
WOS研究方向	Computer Science ; Linguistics
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Linguistics
WOS记录号	WOS:001281001900276
出版者	ASSOC COMPUTATIONAL LINGUISTICS-ACL
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348156
专题	信息科学与技术学院信息科学与技术学院_PI研究组_屠可伟组信息科学与技术学院_博士生
作者单位	1.Alibaba Grp, DAMO Acad, Hangzhou, Peoples R China 2.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou, Peoples R China 3.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 4.Tsinghua Univ, Tsinghua Shenzhen Int Grad Sch, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Tan, Zeqi,Huang, Shen,Jia, Zixia,et al. DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition[C]. 209 N EIGHTH STREET, STROUDSBURG, PA 18360 USA:ASSOC COMPUTATIONAL LINGUISTICS-ACL,2023.