Part of Speech Tagging for Indonesian Language using Bidirectional Long Short-Term Memory

被引:0
作者
Handrata, Dellon [1 ]
Purwanto, Christian Nathaniel [1 ]
Chandra, Fransisca Haryanti [2 ]
Santoso, Joan [1 ]
Gunawan [1 ]
机构
[1] Inst Sains & Teknol Terpadu Surabaya, Dept Informat Technol, Surabaya, Indonesia
[2] Inst Sains & Teknol Terpadu Surabaya, Dept Informat, Surabaya, Indonesia
来源
2019 1ST INTERNATIONAL CONFERENCE ON CYBERNETICS AND INTELLIGENT SYSTEM (ICORIS) | 2019年
关键词
part of speech tagging; Indonesian language; bidirectional long short-term memory; natural language processing; deep learning;
D O I
10.1109/icoris.2019.8874871
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Part of Speech (POS) is a label to distinguish a word based on its grammatical and morphological form. By providing the POS label, we can get the contextual meaning. This label can be used as contextual features for several computational linguistic research - for example, word sense disambiguation, chunking, machine translation, and sequence classification. Our work is done by using bidirectional long short-term memory to do the part of speech tagging task for Bahasa Indonesia. We use deep learning model for Indonesia language POS tagging because deep learning can achieve excellent performance on it. We could reach 96.92% of F1 Score based on our approach.
引用
收藏
页码:85 / 88
页数:4
相关论文
共 22 条
[21]   Feature-rich part-of-speech tagging with a cyclic dependency network [J].
Toutanova, K ;
Klein, D ;
Manning, CD ;
Singer, Y .
HLT-NAACL 2003: HUMAN LANGUAGE TECHNOLOGY CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE MAIN CONFERENCE, 2003, :252-259
[22]  
Ueffing N, 2003, EACL 2003: 10TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, P347