Structured Tuning for Semantic Role Labeling
Structured Tuning for Semantic Role Labeling
复制标题
DOI：
10.18653/v1/2020.acl-main.744
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Tao Li;Parth Anand Jawale;M. Palmer;Vivek Srikumar
中科院分区：
文献类型：
--
作者：
Tao Li;Parth Anand Jawale;M. Palmer;Vivek Srikumar
最近，神经网络驱动的语义角色标记(SRL)系统在F1成绩方面显示出令人印象深刻的改善。这些改进归功于可表达的输入表示，至少在表面上，它与帮助线性SRL模型的知识丰富的约束解码机制是正交的。引入结构的好处来为神经模型提供信息是一个方法论挑战。在本文中，我们提出了一个结构化的调整框架，只在训练时使用软化的约束来改进模型。我们的框架利用了神经网络的表达能力，并提供了结构化损失分量的监督。我们从一个强基线(Roberta)开始验证我们方法的影响，并通过学习遵守声明性约束来展示我们的框架优于基线。此外，我们在较小训练规模下的实验表明，在低资源场景下，我们可以获得一致的改进。
Recent neural network-driven semantic role labeling (SRL) systems have shown impressive improvements in F1 scores. These improvements are due to expressive input representations, which, at least at the surface, are orthogonal to knowledge-rich constrained decoding mechanisms that helped linear SRL models. Introducing the benefits of structure to inform neural models presents a methodological challenge. In this paper, we present a structured tuning framework to improve models using softened constraints only at training time. Our framework leverages the expressiveness of neural networks and provides supervision with structured loss components. We start with a strong baseline (RoBERTa) to validate the impact of our approach, and show that our framework outperforms the baseline by learning to comply with declarative constraints. Additionally, our experiments with smaller training sizes show that we can achieve consistent improvements under low-resource scenarios.