Semantic Role Labeling: A Systematical Survey
This survey is significant for NLP researchers and practitioners as it provides a systematic and comprehensive overview of the SRL field, addressing the lack of a thorough organization of the existing research.
This paper tackles the problem of understanding the current state of semantic role labeling (SRL) research by providing a comprehensive survey of the field over the past two decades, resulting in a thorough organization and synthesis of SRL methodologies and applications. The survey covers various aspects, including model architectures, syntax feature modeling, and practical applications, but does not report specific numerical results.
Semantic role labeling (SRL) is a central natural language processing (NLP) task aiming to understand the semantic roles within texts, facilitating a wide range of downstream applications. While SRL has garnered extensive and enduring research, there is currently a lack of a comprehensive survey that thoroughly organizes and synthesizes the field. This paper aims to review the entire research trajectory of the SRL community over the past two decades. We begin by providing a complete definition of SRL. To offer a comprehensive taxonomy, we categorize SRL methodologies into four key perspectives: model architectures, syntax feature modeling, application scenarios, and multi-modal extensions. Further, we discuss SRL benchmarks, evaluation metrics, and paradigm modeling approaches, while also exploring practical applications across various domains. Finally, we analyze future research directions in SRL, addressing the evolving role of SRL in the age of large language models (LLMs) and its potential impact on the broader NLP landscape. We maintain a public repository and consistently update related resources at: https://github.com/DreamH1gh/Awesome-SRL