We propose Structured Language Generation Model (SLGM), a mixture of new loss function and inference method for better generalization of structured outputs. Previous studies on structure prediction (e.g. NER, RE) make use of explicit dataset information, which would boost performance, yet it might pose challenges to robust generalization in real-world situations. Instead, our model gives generalized format information about data indirectly. With format information, we could reduce sequence-to-sequence problem into classification problem via loss calibration and formatted decoding. Our experimental results showed SLGM successfully maintain performance without dataset information, and showed much less format errors. We also showed our model can work like adapters on individual dataset, with no additional training.

翻译：我们提出了结构化语言生成模型（SLGM），这是一种融合新损失函数与推理方法的模型，旨在提升结构化输出的泛化能力。以往的结构预测研究（如命名实体识别、关系抽取）借助显式的数据集信息来提升性能，但这可能在实际场景中给稳健泛化带来挑战。相比之下，我们的模型以间接方式提供数据的广义格式信息。借助格式信息，我们能够通过损失校准与格式化解码，将序列到序列问题简化为分类问题。实验结果表明，SLGM 在无需数据集信息的情况下成功维持了性能，且格式错误显著减少。我们还展示了该模型可像适配器一样在单个数据集上运行，无需额外训练。