PAI at SemEval-2023 Task 2: A Universal System for Named Entity Recognition with External Entity Information
This addresses the problem of named entity recognition in challenging, noisy, and low-context settings for NLP researchers and practitioners, representing an incremental improvement through integration of external knowledge.
The paper tackled the MultiCoNER II task of detecting complex, ambiguous, and fine-grained named entities in low-context and noisy scenarios across multiple languages by integrating external entity information from Wikipedia into Transformer-based models, resulting in winning 2 first places, 4 second places, and 1 third place out of 13 tracks.
The MultiCoNER II task aims to detect complex, ambiguous, and fine-grained named entities in low-context situations and noisy scenarios like the presence of spelling mistakes and typos for multiple languages. The task poses significant challenges due to the scarcity of contextual information, the high granularity of the entities(up to 33 classes), and the interference of noisy data. To address these issues, our team {\bf PAI} proposes a universal Named Entity Recognition (NER) system that integrates external entity information to improve performance. Specifically, our system retrieves entities with properties from the knowledge base (i.e. Wikipedia) for a given text, then concatenates entity information with the input sentence and feeds it into Transformer-based models. Finally, our system wins 2 first places, 4 second places, and 1 third place out of 13 tracks. The code is publicly available at \url{https://github.com/diqiuzhuanzhuan/semeval-2023}.