An Empirical Study of Span Representations in Argumentation Structure Parsing

  • Tatsuki Kuribayashi
    Graduate School of Information Sciences, Tohoku University Langsmith Inc.
  • Ouchi Hiroki
    Graduate School of Information Sciences, Tohoku University RIKEN Center for Advanced Intelligence Project
  • Inoue Naoya
    Graduate School of Information Sciences, Tohoku University RIKEN Center for Advanced Intelligence Project Present affiliation: Stony Brook University
  • Suzuki Jun
    Graduate School of Information Sciences, Tohoku University RIKEN Center for Advanced Intelligence Project
  • Reisert Paul
    RIKEN Center for Advanced Intelligence Project
  • Miyoshi Toshinori
    Research & Development Group, Hitachi, Ltd.
  • Inui Kentaro
    Graduate School of Information Sciences, Tohoku University RIKEN Center for Advanced Intelligence Project

Bibliographic Information

Other Title
  • 論述構造解析におけるスパン分散表現
  • ロンジュツ コウゾウ カイセキ ニ オケル スパン ブンサン ヒョウゲン

Search this article

Description

<p> Argumentation Structure Parsing (ASP) is the task of predicting the roles of argumentative units (e.g., claim, premise) and the relations between the units (e.g., support, attack) in an argumentative text. ASP has received a great deal of attention due to its usefulness for applications such as automatic assessment of argumentative texts. As textual spans (i.e., argumentative units) are basic units of ASP, it is important to explore an effective design for representing them. Inspired by the current span representation design in other natural language processing tasks, we propose a method to obtain effective span representations of argumentative units in ASP. Our proposed method leverages multiple levels of global contextual information, such as argumentative markers in surrounding contexts, for obtaining each span representation. We show that using our span representation improves performance on several benchmark datasets—especially when parsing complex argumentative texts, which have been difficult to parse with existing methods. Furthermore, we report the effectiveness of our span representations when using word representations obtained from existing, powerful language models such as BERT. </p>

Journal

References(37)*help

See more

Details 詳細情報について

Report a problem

Back to top