06月14日(Thu) 09:00〜12:20 P会場(-ふるさと伝承センターみやび館／和室(1軒屋(50坪)))
| 演題番号 | 3P1-IOS-2a-3 |
|---|---|
| 題目 | Extracting Definitions of Mathematical Expressions in Scientific Papers |
| 著者 | Kristianto Giovanni Yoko(The University of Tokyo) Nghiem Minh-Quoc(The Graduate University for Advanced Studies) Matsubayashi Yuichiroh(National Institute of Informatics) Akiko Aizawa(The University of Tokyo) |
| 時間 | 06月14日(Thu) 10:00〜10:30 |
| 概要 | Natural language definitions of mathematical expressions often play an essential role to understand mathematical content of scientific papers. However, there exists no available annotated data that contains relations between mathematical expressions and their definitions. Such annotated data enables us to apply and compare different approaches for this relation extraction task. In this paper, we first introduce our guideline for annotating definitions of mathematical expressions in scientific papers. This guideline describes specific types of mathematical expression description that should be annotated as definitions and how to annotate them. Based on the guideline, we manually annotated 14 papers from International Journal on Document Analysis and Recognition (IJDAR) from Springer. We also developed and investigated the performance of pattern matching and machine learning based methods in comparison with an existing naive practice that is based on the head noun of preceding text. |
| 論文 | PDFファイル |