arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.00496cs.CLcs.LG
收藏

语义角色标注的结构化调优

Structured Tuning for Semantic Role Labeling

University of Utah(犹他大学);University of Colorado(科罗拉多大学)

Tao Li, Parth Anand Jawale, Martha Palmer, Vivek Srikumar

摘要:

最近的神经网络驱动的语义角色标注(SRL)系统在F1分数方面表现出令人印象深刻的改善。这些改进是由于富有表现力的输入表示,至少在表面上,与帮助线性SRL模型的知识丰富的约束解码机制正交。引入结构的好处来为神经模型提供信息是一个方法上的挑战。在本文中,我们提出了一个结构化的调整框架,以改善模型使用软化的约束,只有在训练时。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组件的监督。我们从一个强大的基线(RoBERTa)开始验证我们的方法的影响,并表明我们的框架通过学习遵守声明性约束来超越基线。此外,我们对较小训练规模的实验表明,我们可以在低资源场景下实现一致的改进。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑