Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm
This work addresses semantic parsing for natural language processing applications, presenting incremental improvements through architectural optimization and data augmentation.
The paper tackles Universal Decompositional Semantic (UDS) parsing by introducing a cascade model that decomposes the task into subtasks, outperforming prior models and reducing inference time, while also exploring data augmentation and evaluating ChatGPT's performance, which excels in attribute parsing but struggles in relation parsing.
In this paper, we conduct a holistic exploration of the Universal Decompositional Semantic (UDS) Parsing. We first introduce a cascade model for UDS parsing that decomposes the complex parsing task into semantically appropriate subtasks. Our approach outperforms the prior models, while significantly reducing inference time. We also incorporate syntactic information and further optimized the architecture. Besides, different ways for data augmentation are explored, which further improve the UDS Parsing. Lastly, we conduct experiments to investigate the efficacy of ChatGPT in handling the UDS task, revealing that it excels in attribute parsing but struggles in relation parsing, and using ChatGPT for data augmentation yields suboptimal results. Our code is available at https://github.com/hexuandeng/HExp4UDS.