Home >

news Help

Publication Information


Title
Japanese: 
English:Metric-Type Identification for Multi-Level Header Numerical Tables in Scientific Papers 
Author
Japanese: Lya Hulliyyatus Suadaa, 上垣外 英剛, 奥村 学, 高村 大也.  
English: Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Manabu Okumura, Hiroya Takamura.  
Language English 
Journal/Book name
Japanese: 
English:Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics 
Volume, Number, Page Main Volume        Page 3062–3071
Published date Apr. 19, 2021 
Publisher
Japanese: 
English:Association for Computational Linguistics (ACL) 
Conference name
Japanese: 
English:The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021) 
Conference site
Japanese: 
English: 
Official URL https://www.aclweb.org/anthology/2021.eacl-main.267/
 
Abstract Numerical tables are widely used to present experimental results in scientific papers. For table understanding, a metric-type is essential to discriminate numbers in the tables. We introduce a new information extraction task, metric-type identification from multi-level header numerical tables, and provide a dataset extracted from scientific papers consisting of header tables, captions, and metric-types. We then propose two joint-learning neural classification and generation schemes featuring pointer-generator-based and BERT-based models. Our results show that the joint models can handle both in-header and out-of-header metric-type identification problems.

©2007 Tokyo Institute of Technology All rights reserved.