复现经典序列标注模型，验证其在命名实体识别上的高精度表现。
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF: A Reproducibility Study
- 用双向LSTM+CNN+CRF构建端到端序列标注框架
- 在CoNLL-2003数据集上达到91.18%的F1分数
- 开源代码助力后续研究，适合学习序列建模者
我们对Ma和Hovy（2016）提出的序列标注前沿神经架构进行了可复现性研究。原始的BiLSTM-CNN-CRF模型通过卷积神经网络（CNNs）获取字符级表示，利用双向长短期记忆网络（BiLSTMs）建模词级上下文，并采用条件随机场（CRFs）进行结构化预测。该端到端方法无需手工特征设计，即可在命名实体识别（NER）和词性标注（POS）任务上取得优异性能。我们的实现成功复现了关键结果，在CoNLL-2003 NER任务上达到91.18%的F1分数，验证了该模型在序列标注任务中的有效性。我们对各组件进行了详细分析，并发布开源的PyTorch实现，以促进后续研究。
原文摘要 · Abstract (English)
We present a reproducibility study of the state-of-the-art neural architecture for sequence labeling proposed by Ma and Hovy (2016)\cite{ma2016end}. The original BiLSTM-CNN-CRF model combines character-level representations via Convolutional Neural Networks (CNNs), word-level context modeling through Bi-directional Long Short-Term Memory networks (BiLSTMs), and structured prediction using Conditional Random Fields (CRFs). This end-to-end approach eliminates the need for hand-crafted features while achieving excellent performance on named entity recognition (NER) and part-of-speech (POS) tagging tasks. Our implementation successfully reproduces the key results, achieving 91.18\% F1-score on CoNLL-2003 NER and demonstrating the model's effectiveness across sequence labeling tasks. We provide a detailed analysis of the architecture components and release an open-source PyTorch implementation to facilitate further research.
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。