探索新型模型在序列标注中的适用性，发现复杂任务下表现不稳定。
Bringing Emerging Architectures to Sequence Labeling in NLP
- 测试 xLSTM、状态空间模型等新架构在序列标注中的表现
- 复杂任务和多语言场景下性能不如预训练Transformer
- 提醒研究者注意模型泛化能力的局限性
预训练Transformer编码器是序列标注的主流方法。尽管xLSTM、结构化状态空间模型、扩散模型和对抗学习等替代架构在语言建模中展现出潜力，但极少被应用于序列标注，且多限于简单或扁平任务。本文研究这些架构在结构复杂度、标签空间和词元依赖性各异的标注任务中的适应性，涵盖多种语言。结果表明，先前在简单设置中观察到的优异性能，并未在跨语言或不同数据集间良好泛化，也无法延伸至更复杂的结构化任务。
原文摘要 · Abstract (English)
Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models, and adversarial learning-have shown promise in language modeling, few have been applied to sequence labeling, and mostly on flat or simplified tasks. We study how these architectures adapt across tagging tasks that vary in structural complexity, label space, and token dependencies, with evaluation spanning multiple languages. We find that the strong performance previously observed in simpler settings does not always generalize well across languages or datasets, nor does it extend to more complex structured tasks.
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。