Linguistic analysis of digitized academic papers(<Special feature>Japanese language in the digital era)
-
- AIZAWA Akiko
- National Institute of Informatics
Bibliographic Information
- Other Title
-
- デジタル化された学術文献の言語解析について(<特集>デジタル時代の日本語)
- デジタル化された学術文献の言語解析について
- デジタルカ サレタ ガクジュツ ブンケン ノ ゲンゴ カイセキ ニ ツイテ
Search this article
Abstract
Document digitization in academic field enables us to apply automatic linguistic analysis to a large volume of academic papers. While current implementations of retrieval systems is mainly based on naive and shallow keyword extraction techniques, more advanced systems may leverage deeper linguistic analysis to help users easily access necessary papers or gain overview of a particular research field. In this paper, we first give a brief introduction to major natural language processing tasks targeting academic papers. Next, we describe methods for extracting natural language sentences and technical terms from digitized academic papers, with their difficulties and possible applications for each method.
Journal
-
- The Journal of Information Science and Technology Association
-
The Journal of Information Science and Technology Association 64 (11), 469-474, 2014
Information Science and Technology Association, Japan
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282679152664832
-
- NII Article ID
- 110009865883
-
- NII Book ID
- AN10005857
-
- ISSN
- 21898278
- 09133801
-
- NDL BIB ID
- 025876213
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- CiNii Articles
-
- Abstract License Flag
- Allowed