# DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition arXiv: https://arxiv.org/abs/2305.03688 ยท HTML: https://mlsanity.com/paper/2305.03688/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. - Builds on 27 of its 51 references that are in the map. - First posted on arXiv 5 May 2023. ## Placed in - Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/) ## Builds on (most cited first, 27 of 27) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022) - [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023) - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020) - [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019) - [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022) - [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017) - [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021) - [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019) - [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020) - [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention](https://mlsanity.com/paper/2010.01057/) (2020) - [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023) - [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023) - [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023) - [GPT-NER: Named Entity Recognition via Large Language Models](https://mlsanity.com/paper/2304.10428/) (2023) - [Automated Concatenation of Embeddings for Structured Prediction](https://mlsanity.com/paper/2010.05006/) (2020) - [Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning](https://mlsanity.com/paper/2105.03654/) (2021) - [EntQA: Entity Linking as Question Answering](https://mlsanity.com/paper/2110.02369/) (2021) - [Named Entity and Relation Extraction with Multi-Modal Retrieval](https://mlsanity.com/paper/2212.01612/) (2022) - [DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition](https://mlsanity.com/paper/2203.00545/) (2022) - [Domain-Specific NER via Retrieving Correlated Samples](https://mlsanity.com/paper/2208.12995/) (2022) - [Targetable Named Entity Recognition in Social Media](https://mlsanity.com/paper/1408.0782/) (2014) - [USTC-NELSLIP at SemEval-2022 Task 11: Gazetteer-Adapted Integration Network for Multilingual Complex Named Entity Recognition](https://mlsanity.com/paper/2203.03216/) (2022) - [More Embeddings, Better Sequence Labelers?](https://mlsanity.com/paper/2009.08330/) (2020) - [TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning](https://mlsanity.com/paper/2107.06907/) (2021) - [Qtrade AI at SemEval-2022 Task 11: An Unified Framework for Multilingual NER Task](https://mlsanity.com/paper/2204.07459/) (2022) ## Built on by (most cited first, 9 of 9) - [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023) - [SemEval-2023 Task 2: Fine-grained Multilingual Named Entity Recognition (MultiCoNER 2)](https://mlsanity.com/paper/2305.06586/) (2023) - [Refine Knowledge of Large Language Models via Adaptive Contrastive Learning](https://mlsanity.com/paper/2502.07184/) (2025) - [AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees](https://mlsanity.com/paper/2512.04550/) (2025) - [Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking](https://mlsanity.com/paper/2306.12245/) (2023) - [RATSF: Empowering Customer Service Volume Management through Retrieval-Augmented Time-Series Forecasting](https://mlsanity.com/paper/2403.04180/) (2024) - [Transformer-based Named Entity Recognition with Combined Data Representation](https://mlsanity.com/paper/2406.17474/) (2024) - [Entity Identifier: A Natural Text Parsing-based Framework For Entity Relation Extraction](https://mlsanity.com/paper/2307.04892/) (2023) - [RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models](https://mlsanity.com/paper/2505.19128/) (2025) ## Abstract (arXiv) The MultiCoNER RNum2 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 RNum1 task. To cope with these problems, the previous top systems in the MultiCoNER RNum1 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 systemfootnoteWe will release the dataset, code, and scripts of our system at small urlhttps://github.com/modelscope/AdaSeq/tree/master/examples/U-RaNER. wins 9 out of 13 tracks in the MultiCoNER RNum2 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.