用Transformer模型提升症状识别与链接的准确率

Team Fusion@ SU@ BC8 SympTEMIST track: transformer-based approach for symptom recognition and linking

• 基于RoBERTa微调，结合BiLSTM与CRF做症状实体识别
• 通过SapBERT生成候选实体，用余弦相似度匹配知识库
• 知识库选择对性能影响最大，是关键优化点

本文提出一种基于Transformer的方案，用于解决SympTEMIST任务中的命名实体识别（NER）与实体链接（EL）。在NER阶段，我们在增强训练集上对RoBERTa模型进行微调，并加入BiLSTM与CRF层以实现分词级分类。实体链接则通过跨语言SapBERT XLMR-Large生成候选实体，并计算其与知识库之间的余弦相似度完成匹配。实验表明，知识库的选择对模型精度影响最大。

原文摘要 · Abstract (English)

This paper presents a transformer-based approach to solving the SympTEMIST named entity recognition (NER) and entity linking (EL) tasks. For NER, we fine-tune a RoBERTa-based (1) token-level classifier with BiLSTM and CRF layers on an augmented train set. Entity linking is performed by generating candidates using the cross-lingual SapBERT XLMR-Large (2), and calculating cosine similarity against a knowledge base. The choice of knowledge base proves to have the highest impact on model accuracy.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。