Granular syntax processing with multi-task and curriculum learning

• Main Authors: Zhang, Xulang, Mao, Rui, Cambria, Erik
• Other Authors: College of Computing and Data Science
• Format: Article
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Text chunking; Curriculum learning
• Online Access: https://hdl.handle.net/10356/180666
• Institution: Nanyang Technological University

Syntactic processing techniques are the foundation of natural language processing (NLP), supporting many downstream NLP tasks. In this paper, we conduct pair-wise multi-task learning (MTL) on syntactic tasks with different granularity, namely Sentence Boundary Detection (SBD), text chunking, and Par...