For several natural language processing (NLP) tasks, span representation is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such basis, exploring task-dependent extensions for argumentation structure parsing (ASP) becomes an interesting research direction. This study investigates (ⅰ) span representation originally developed for other NLP tasks and (ⅱ) a simple task-dependent extension for ASP. Our extensive experiments and analysis show that these representations yield high performance for ASP and provide some challenging types of instances to be parsed.
展开▼