Can I read Structured Tuning for Semantic Role Labeling on EtoBox?

Structured Tuning for Semantic Role Labeling by Li, Tao; Jawale, Parth Anand; Palmer, Martha; Srikumar, Vivek is a scholarly article available to read on EtoBox.

What is Structured Tuning for Semantic Role Labeling about?

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.

Author

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

Published

2020

Language

EN