Structured Language Generation Model for Robust Structure Prediction

Previous work in structured prediction (e.g. NER, information extraction) using single model make use of explicit dataset information, which helps boost in-distribution performance but is orthogonal to robust generalization in real-world situations. To overcome this limitation, we propose the Structured Language Generation Model (SLGM), a framework that reduces sequence-to-sequence problems to classification problems via methodologies in loss calibration and decoding method. Our experimental results show that SLGM is able to maintain performance without explicit dataset information, follow and potentially replace dataset-specific fine-tuning.

先前在结构化预测（例如命名实体识别、信息抽取）中使用单一模型的工作利用了明确的数据集信息，这有助于提高分布内的性能，但与现实世界情况下的稳健泛化无关。为了克服这一限制，我们提出了结构化语言生成模型（SLGM），这是一个通过损失校准和解码方法将序列到序列问题简化为分类问题的框架。我们的实验结果表明，SLGM能够在没有明确数据集信息的情况下保持性能，遵循并有可能取代特定于数据集的微调。